hypothesis being used in a sentence

• Conjunctions
• Prepositions

HYPOTHESIS in a Sentence Examples: 21 Ways to Use Hypothesis

Have you ever wondered what a “hypothesis” is and how it fits into the scientific method? A hypothesis is a proposed explanation or educated guess that can be tested through research and experimentation to determine its validity.

In scientific inquiry, a hypothesis serves as the foundation for the study, guiding the direction of the research and helping to form conclusions based on the results. By formulating clear hypotheses, researchers can systematically investigate phenomena and gather evidence to support their claims.

Table of Contents

7 Examples Of Hypothesis Used In a Sentence For Kids

• Hypothesis is a guess we can test.
• We can make a hypothesis about what will happen.
• Our hypothesis will help us learn new things.
• Let’s think of a hypothesis to investigate.
• We can use our hypothesis to solve a problem.
• A good hypothesis can help us understand the world.
• Remember, our hypothesis is just a starting point.

14 Sentences with Hypothesis Examples

• Hypothesis : Students who study for at least 3 hours every day are likely to perform better in their exams.
• It is important for college students to form a hypothesis before conducting any research project.
• Hypothesis : Attending lectures regularly can significantly improve academic performance.
• College students can test their hypothesis through interactive experiments and surveys.
• Hypothesis : Using different study methods can have varied effects on information retention.
• It is necessary for students to critically analyze data to support or reject their hypothesis .
• Hypothesis : Students who engage in extracurricular activities may have a better overall college experience.
• In a scientific study, researchers must clearly define their hypothesis before proceeding with the experiment.
• Hypothesis : Regular exercise can positively impact a student’s mental health and academic performance.
• It is crucial for college students to document their hypothesis and research findings accurately.
• Hypothesis : Students who limit their social media usage may experience improved focus and productivity.
• College projects often require students to brainstorm and formulate a solid hypothesis .
• It is common for students to revise their hypothesis based on new information or research outcomes.
• Hypothesis : Implementing study breaks can enhance retention and understanding of complex subjects.

How To Use Hypothesis in Sentences?

Hypothesis is an educated guess or prediction that can be tested through observation or experimentation. When incorporating this term into a sentence, it is important to clearly identify it so readers can understand its significance.

Here are some tips on how to use hypothesis effectively in a sentence:

Clearly state your hypothesis in a simple and concise manner. For example, “The scientist’s hypothesis is that plants will grow faster with added sunlight.”

Use the word hypothesis to introduce your prediction or expectation before testing it. For instance, “Our hypothesis is that students who study regularly will perform better on the exam.”

Make sure to refer back to your hypothesis when discussing the results of your experiment. For example, “The data supported our initial hypothesis that exercise leads to improved cardiovascular health.”

You can also use the word hypothesis when comparing multiple predictions. For instance, “There are several hypotheses about the cause of the mysterious illness, but more research is needed to determine the correct one.”

By following these guidelines, you can effectively incorporate hypothesis into your writing to communicate your predictions or expectations clearly and accurately.

In conclusion, sentences with the keyword “hypothesis” often express a proposed explanation or prediction that can be tested through research or observation. These sentences play a crucial role in scientific inquiry by guiding investigations and exploring relationships between variables. For example, “The researchers formulated a hypothesis to predict the effect of sunlight on plant growth” demonstrates how hypotheses are used to frame a study’s objectives and outcomes.

Clear and concise sentences with hypotheses are essential for building a solid foundation for scientific exploration and discovery. They provide a starting point for experiments, helping researchers to structure their methodologies and draw meaningful conclusions. By carefully crafting hypotheses, scientists can effectively test their theories, gather evidence, and contribute to the advancement of knowledge in various fields.

Related Posts

In Front or Infront: Which Is the Correct Spelling?

As an expert blogger with years of experience, I’ve delved…  Read More » In Front or Infront: Which Is the Correct Spelling?

Targeted vs. Targetted: Correct Spelling Explained in English (US) Usage

Are you unsure about whether to use “targetted” or “targeted”?…  Read More » Targeted vs. Targetted: Correct Spelling Explained in English (US) Usage

As per Request or As per Requested: Understanding the Correct Usage

Having worked in various office environments, I’ve often pondered the…  Read More » As per Request or As per Requested: Understanding the Correct Usage

Examples of 'hypothesis' in a sentence

Examples from collins dictionaries, examples from the collins corpus.

Quick word challenge

Quiz Review

Score: 0 / 5

All ENGLISH words that begin with 'H'

• More from M-W
• To save this word, you'll need to log in. Log In

Definition of hypothesis

Did you know.

The Difference Between Hypothesis and Theory

A hypothesis is an assumption, an idea that is proposed for the sake of argument so that it can be tested to see if it might be true.

In the scientific method, the hypothesis is constructed before any applicable research has been done, apart from a basic background review. You ask a question, read up on what has been studied before, and then form a hypothesis.

A hypothesis is usually tentative; it's an assumption or suggestion made strictly for the objective of being tested.

A theory , in contrast, is a principle that has been formed as an attempt to explain things that have already been substantiated by data. It is used in the names of a number of principles accepted in the scientific community, such as the Big Bang Theory . Because of the rigors of experimentation and control, it is understood to be more likely to be true than a hypothesis is.

In non-scientific use, however, hypothesis and theory are often used interchangeably to mean simply an idea, speculation, or hunch, with theory being the more common choice.

Since this casual use does away with the distinctions upheld by the scientific community, hypothesis and theory are prone to being wrongly interpreted even when they are encountered in scientific contexts—or at least, contexts that allude to scientific study without making the critical distinction that scientists employ when weighing hypotheses and theories.

The most common occurrence is when theory is interpreted—and sometimes even gleefully seized upon—to mean something having less truth value than other scientific principles. (The word law applies to principles so firmly established that they are almost never questioned, such as the law of gravity.)

This mistake is one of projection: since we use theory in general to mean something lightly speculated, then it's implied that scientists must be talking about the same level of uncertainty when they use theory to refer to their well-tested and reasoned principles.

The distinction has come to the forefront particularly on occasions when the content of science curricula in schools has been challenged—notably, when a school board in Georgia put stickers on textbooks stating that evolution was "a theory, not a fact, regarding the origin of living things." As Kenneth R. Miller, a cell biologist at Brown University, has said , a theory "doesn’t mean a hunch or a guess. A theory is a system of explanations that ties together a whole bunch of facts. It not only explains those facts, but predicts what you ought to find from other observations and experiments.”

While theories are never completely infallible, they form the basis of scientific reasoning because, as Miller said "to the best of our ability, we’ve tested them, and they’ve held up."

• proposition
• supposition

hypothesis , theory , law mean a formula derived by inference from scientific data that explains a principle operating in nature.

hypothesis implies insufficient evidence to provide more than a tentative explanation.

theory implies a greater range of evidence and greater likelihood of truth.

law implies a statement of order and relation in nature that has been found to be invariable under the same conditions.

Examples of hypothesis in a Sentence

These examples are programmatically compiled from various online sources to illustrate current usage of the word 'hypothesis.' Any opinions expressed in the examples do not represent those of Merriam-Webster or its editors. Send us feedback about these examples.

Word History

Greek, from hypotithenai to put under, suppose, from hypo- + tithenai to put — more at do

1641, in the meaning defined at sense 1a

Phrases Containing hypothesis

• counter - hypothesis
• nebular hypothesis
• null hypothesis
• planetesimal hypothesis
• Whorfian hypothesis

Articles Related to hypothesis

This is the Difference Between a...

This is the Difference Between a Hypothesis and a Theory

In scientific reasoning, they're two completely different things

Dictionary Entries Near hypothesis

hypothermia

hypothesize

Cite this Entry

“Hypothesis.” Merriam-Webster.com Dictionary , Merriam-Webster, https://www.merriam-webster.com/dictionary/hypothesis. Accessed 29 May. 2024.

Kids Definition

Kids definition of hypothesis, medical definition, medical definition of hypothesis, more from merriam-webster on hypothesis.

Nglish: Translation of hypothesis for Spanish Speakers

Britannica English: Translation of hypothesis for Arabic Speakers

Britannica.com: Encyclopedia article about hypothesis

Subscribe to America's largest dictionary and get thousands more definitions and advanced search—ad free!

Can you solve 4 words at once?

Word of the day, obstreperous.

See Definitions and Examples »

Get Word of the Day daily email!

Popular in Grammar & Usage

More commonly misspelled words, commonly misspelled words, how to use em dashes (—), en dashes (–) , and hyphens (-), absent letters that are heard anyway, how to use accents and diacritical marks, popular in wordplay, pilfer: how to play and win, the words of the week - may 24, flower etymologies for your spring garden, 9 superb owl words, 10 words for lesser-known games and sports, games & quizzes.

Understanding a Hypothesis (Definition, Null, and Examples)

You come home exhausted and plop down on the couch. You don’t know why you are feeling so weary. You think about several possible reasons. Is it because you stayed up late last night? Is it because you skipped breakfast? Or is it because you had to take the stairs due to a power outage? Or is it because of all the above reasons?

What you are doing is hypothesizing about why you are feeling tired.

If you enjoy reading detective stories, you would have already come across a hypothesis. A good whodunit mystery confounds the reader with multiple hypotheses about who committed the crime.

• What is a Hypothesis?

The term hypothesis is often used in a scientific context as a possible explanation for an occurrence.

The word originated from ancient Greek and means “putting under” indicating its early association with experimentation.

A hypothesis is:

• An assumption that serves as a starting point for further research
• A supposition made on the basis of insufficient evidence
• A tentative and logical statement that can be tested for its authenticity
• An idea that seeks to explain why a phenomenon takes place
• A prediction about the outcome of a study according to known facts
• A proposal about the possible relationship between two or more variables

A scientist testing a hypothesis is no different from a detective investigating a crime scene. Famous detectives such as Sherlock Holmes combine the evidence with their powers of prediction to identify the criminal from several potential suspects.

The scientist examines each hypothesis rigorously for any inconsistencies through experiments before it can receive the stamp of approval.

Scientists accept a hypothesis as a theory only after it has been validated several times in different conditions. This includes use of scientific methods and protocols involving observation and analysis of results.

A good hypothesis seeks to establish a causal relationship between two or more variables, primarily between the independent and the dependent variable.

Brushing your teeth at least twice in a day reduces the incidence of dental caries.

The independent variable or cause in the above example is the number of times you brush in a day. The dependent variable or effect is the incidence of dental caries or cavities.

A scientist or researcher tests a hypothesis by changing the independent variable and measuring its effect on the dependent variable.

A relationship between a single independent and dependent variable is known as a simple hypothesis.

The mathematical expression of this relationship is:

• where x is the independent variable and Y is the dependent variable and
• where x is the input and Y is the output or a function of x

So, brushing your teeth at least twice daily is an input and the reduction of dental caries is an output or a function of the action of brushing your teeth. 

If there are multiple independent variables or in some cases more than a single dependent variable, the statement is a complex hypothesis.

Brushing your teeth at least twice a day and using dental floss reduces the incidence of cavities and periodontitis.

In the above example the two independent variables are brushing teeth and using dental floss. The dependent variables are reduction in cavities and periodontitis or gum infection. In this example the two independent variables are common for the two dependent variables.

The equation of a complex hypothesis can be written as:

Y = f(x 1 +x 2 +x 3 …)

Y 1 = f(z 1 +z 2 +z 3 …)

where z is a different set of independent variables for Y1 as the dependent variable

• Developing a Hypothesis

A hypothesis is a frame of reference or a window through which you observe a phenomenon. The phenomenon is the dependent variable. Your job is to determine the independent variables that are causing the event.

Cultivate the habit of looking for patterns in anything that happens. Train your mind to think in terms of stimulus and reaction or cause and effect.

This will enable you to glean insights from the knowledge you gather. You will then be able to write a strong hypothesis that focuses on the variables that matter over the noise.

The six steps to developing a hypothesis are:

• Ask a question
• Preliminary research
• Formulate the hypothesis
• Refine the hypothesis
• Phrase your hypothesis in three ways
• Write a null hypothesis

Ask a Question

The first step is to write a research question.

To write an effective research question be as curious as possible. Start with asking yourself a ton of questions.

Begin with broad and open-ended questions before narrowing it down to more specific ones.

You can use the 5W1H method to get into the mode of writing a research question.

• What took place?
• When did it happen?
• Where did it occur?
• Why did it take place?
• Who did it affect ?
• How did it happen?

The research question needs to be clear, objective , well-defined and measurable.

Do people who take health supplements log in fewer sick days at work in a year than those who don’t?

After you have framed the right question you can make an educated guess to answer it. This answer will be your preliminary hypothesis. Your hypothesis will attempt to answer the research question with observable facts through various experiments.

Preliminary Research

You don’t have to start from scratch. You can draw from preexisting knowledge and well-established theories to discount fallacious premises at the outset.

Resources that you can refer to include case studies, research papers and theses published in academic or scientific journals. A thorough background research will help you to look at the research question from several angles.

Do keep an open mind or a blank slate to avoid falling in the trap of preconceived notions and prejudices. Your initial research should help you focus on the areas where you are most likely to find the answers.

You can come up with a blueprint or outline highlighting the variables that you think are most relevant to your research question.

Think how changing the attributes of a single variable potentially affects others. You may need to operationalize or define how you are going to measure the variables and their effects.

Formulate the Hypothesis

It’s time now to put together your hypothesis into words.

A sound hypothesis states:

• Who or what is being studied?
• The relationship between the variables
• A measurable and reproducible outcome
• The possibility to prove it as true or false

Teenagers in the 14-16 age group who eat a high-protein diet are taller by two inches than the average height for that age group.

The next step is to ensure your statement ticks all the boxes for a strong hypothesis.

Is the hypothesis:

• Precise and quantifiable without any ambiguity
• Lucid and focused on the results described in the research question

Does the hypothesis include:

• An independent and dependent variable
• Variables that can be changed or controlled
• Terms that even a layman can understand
• A well-defined outcome

Phrase your Hypothesis in Three Ways

A hypothesis is often written in an If-then format. This format describes the cause and effect relationship between an independent variable and a dependent variable.

Phrase your hypothesis as “If {you make changes to an independent variable} then {you will observe this change in the dependent variable}.”

If employees are given more autonomy to take work-related decisions then their overall performance improves.

Another way to write a hypothesis is by directly stating the outcome between the two variables.

More autonomy in terms of taking work-related decisions helps to improve an employee’s overall performance.

You can also state a hypothesis as a comparison between two groups.

Employees who are offered more autonomy to take work-related decisions show better overall performance than those who work in a micro-managed environment.

Write a Null Hypothesis

The next step is to frame a null hypothesis, especially if your study requires you to analyze the data statistically. A null hypothesis by default takes a converse position to the researcher’s hypothesis.

Your statement is known as the alternative hypothesis while its opposite outcome is referred to as the null hypothesis.

If you expect a change according to a relationship between the variables the null hypothesis denies the possibility of any change or association between the variables. If you expect the conditions to remain constant the null hypothesis states that change will take place.

The null hypothesis is referred to as H 0. Your hypothesis which is the alternative is written as H 1 or H a .

H 1 : A player who is more than two meters tall has a better chance of winning the National Basketball Association Most Valuable Player Award.

H 0 : The height of a player does not affect his prospects of winning the National Basketball Association Most Valuable Player Award.

Hypothesis Examples

Examples of research questions.

• Which loop diuretic drug is more effective for treating heart failure?
• Does attending online learning sessions help students to improve their exam scores?
• Does talking on the phone while driving cause more accidents?
• Does increasing the pressure affect the rate of reaction between gases?
• Is a person more likely to be obese if she or he eats unhealthy foods at least four times in a week?

Examples of a Hypothesis

• The clinical trial of the new drug Furosemide proved that it is better at treating heart failure than other loop diuretic drugs such as Bumetanide.
• The students who attended online learning sessions had better exam scores than those who skipped the sessions.
• Drivers who talk on the phone are likely to have an accident than those who don’t.
• Increasing the pressure affects the concentration of gases and it acts as a catalyst in speeding up the rate of reaction.
• People who eat processed foods frequently are more likely to be obese than people who limit their intake of such foods.

Examples of a Null Hypothesis

• The clinical trial proved that there is no difference between the effectiveness of Furosemide and other loop diuretic drugs, such as Bumetanide, for treating heart failure.
• There is no difference in the exam scores of students who attended online learning sessions and those who did not attend.
• There is no difference in the rate of accidents experienced by drivers who talk on the phone compared with those who don’t talk on the phone while driving.
• The elevation of pressure has no effect on the rate of reaction between gases.
• The food consumed and its frequency of consumption do not affect the probability of a person becoming obese.

What are Null Hypotheses?

The null hypothesis states the opposite outcome to the researcher’s hypothesis.

In most cases, the null hypothesis’s default position is a prediction that no relationship exists between any two or more variables. The null hypothesis denies the possibility of a causal relationship existing between an assumed independent and dependent variable.

The symbol of the null hypothesis is H 0 .

The notion of a null hypothesis fulfills the requirement of the falsifiability of a hypothesis before it can be accepted as valid.

A null hypothesis is often written as a negative statement that posits that the original hypothesis is false. It either claims that the results obtained are due to chance or there is no evidence to prove any change.

Original Hypothesis: Use of nitrogen fertilizers helps plants grow faster as compared to use of phosphorus or potassium fertilizers. 

Null Hypothesis (H 0 ): The fertilizer used has no bearing on the rate of plant growth

What are Alternative Hypotheses?

An alternative hypothesis states the researcher’s supposition of a causal relationship between any two or more variables. Alternative hypotheses are based upon an observable effect and seek to predict how changing an independent variable will affect the dependent variable.

An alternative hypothesis is symbolized as H 1 or H a . It’s often written together with a null hypothesis with the two statements existing as a dual pair of opposite assumptions. Only a single statement among two can be true.

Alternative hypotheses try to determine that the results are obtained due to significant changes related to the variables and not due to chance.

Research Question: Does washing hands thoroughly with soap before eating a meal reduce the rate of recurrence of respiratory ailments?

Alternative Hypothesis (H 1 ): Washing hands with soap before eating reduces the rate of recurrence of respiratory ailments by 30% compared with those who neglect hand hygiene.

Null Hypothesis (H 0 ): Washing hands with soap before eating has no effect on the rate of recurrence of respiratory ailments. 

What is Hypothesis Testing?

After you have formulated a hypothesis, you need to choose a research and testing method.

Use a descriptive approach when experiments are difficult to conduct. A descriptive method incorporates case studies and surveys to collect data.

You can employ statistical tools such as a correlational study to measure the relationship between variables.

A correlational study calculates the probability of whether a linkage between two variables can be determined or do the changes occur purely due to chance. Do note that correlation is not equivalent to causality.

This method lets you arrive at a conclusion by generalizing the data obtained without performing any actual experiments. A hypothesis proved using this approach is known as a statistical hypothesis.

The other approach is the experimental method in which causal relationships are established between different variables through demonstrations. A working or empirical hypothesis often makes use of the experimental method to determine the relationships between the variables.

The steps for testing a hypothesis experimentally are:

• Design of experiments
• Collating data
• Analysis of observable facts
• Summarizing the conclusions
• Validating the hypothesis as a theory

How to Write a Good Hypothesis

To find ideas for a hypothesis, you can look through discussion sections in academic and scientific journals or browse online publications. You will come across questions that can be investigated further.

Simple Steps

The steps to write a strong hypothesis are:

• Choose your frame of reference or direction for determining the cause
• Such an approach is known as a directional hypothesis
• If you are unable to determine a starting point or the current theories are ambiguous and contradictory, you can choose a non-directional approach
• This method involves stating the facts and observations randomly and then seeking to find a pattern
• Identify the key variables
• A variable is any attribute that can have measurable values such as temperature, time, or length
• Tentatively label some variables as independent and some as dependent
• State the relationship between the variables using clear and objective language
• Operationalize or define how you will measure the variables for testability
• Write the statement in the If-then format. You can also write it as a declarative sentence
• Avoid jargon and use simple words that can be understood by a layman
• Write a null hypothesis to satisfy the condition of falsifiability

If you watch television for more than three hours a day, then your ability to concentrate diminishes.

How to Write a Scientific Hypothesis

A good scientific hypothesis is:

• Consistent: Use preexisting knowledge as a springboard for further research
• Testable: Include words that are quantifiable or measurable
• Concise: Cut down on verbose phrases and use precise words
• Scalable: Formulate the statement in a universal context based on the variables
• Promising: State unexplained occurrences as loose ends that can be investigated further

Simple steps

• Record your observations and facts about the topic
• Evaluate your statements for possible links to determine the cause and effect
• Document all potential explanations to analyze further
• Write the null hypothesis along with your own hypothesis
• This satisfies the requisite condition for a valid hypothesis. It can either be confirmed or disproved

If you plant cotton in black soil, then the production is boosted by 20% as compared to the output from red soil.

How to write a Psychology Hypothesis

A psychology hypothesis often begins with how the environment or certain parameters within it influence or cause a specific behavior.

To write a sound psychology hypothesis:

• Choose a topic that you are genuinely interested in
• Do not ramble. Keep it short and simple
• Use previous research and your own study to direct your vision
• Ascertain and define the variables
• You can write the hypothesis either as an If-then statement
• Other alternatives are to write the hypothesis as a direct sentence or a comparative supposition

Use the following questions to guide your understanding of the topic.

• Is your hypothesis based on a preexisting theory or your own research? 
• Can your hypothesis be tested for falsifiability?
• What are the independent and dependent variables?

People who exercise regularly are less at risk from depression than people who lead a sedentary life.

• What is and How to Write a Good Hypothesis in Research?
• How to Write a Hypothesis in 6 Steps
• Developing Hypothesis and Research Questions
• Forming a Good Hypothesis for Scientific Research
• 6 Hypothesis Examples in Psychology
• Correlational Research | When & How to Use
• How to Write a Strong Hypothesis in 6 Simple Steps
• How to Develop a Good Research Hypothesis
• How To Develop a Hypothesis (With Elements, Types and Examples)
• Definition of Hypothesis

Inside this article

Fact checked: Content is rigorously reviewed by a team of qualified and experienced fact checkers. Fact checkers review articles for factual accuracy, relevance, and timeliness. Learn more.

About the author

Dalia Y.: Dalia is an English Major and linguistics expert with an additional degree in Psychology. Dalia has featured articles on Forbes, Inc, Fast Company, Grammarly, and many more. She covers English, ESL, and all things grammar on GrammarBrain.

Core lessons

• Abstract Noun
• Accusative Case
• Active Sentence
• Alliteration
• Adjective Clause
• Adjective Phrase
• Adverbial Clause
• Appositive Phrase
• Body Paragraph
• Compound Adjective
• Complex Sentence
• Compound Words
• Compound Predicate
• Common Noun
• Comparative Adjective
• Comparative and Superlative
• Compound Noun
• Compound Subject
• Compound Sentence
• Copular Verb
• Collective Noun
• Colloquialism
• Conciseness
• Conditional
• Concrete Noun
• Conjunction
• Conjugation
• Conditional Sentence
• Comma Splice
• Correlative Conjunction
• Coordinating Conjunction
• Coordinate Adjective
• Cumulative Adjective
• Dative Case
• Declarative Statement
• Direct Object Pronoun
• Direct Object
• Dangling Modifier
• Demonstrative Pronoun
• Demonstrative Adjective
• Direct Characterization
• Definite Article
• Doublespeak
• Equivocation Fallacy
• Future Perfect Progressive
• Future Simple
• Future Perfect Continuous
• Future Perfect
• First Conditional
• Gerund Phrase
• Genitive Case
• Helping Verb
• Irregular Adjective
• Irregular Verb
• Imperative Sentence
• Indefinite Article
• Intransitive Verb
• Introductory Phrase
• Indefinite Pronoun
• Indirect Characterization
• Interrogative Sentence
• Intensive Pronoun
• Inanimate Object
• Indefinite Tense
• Infinitive Phrase
• Interjection
• Intensifier
• Indicative Mood
• Juxtaposition
• Linking Verb
• Misplaced Modifier
• Nominative Case
• Noun Adjective
• Object Pronoun
• Object Complement
• Order of Adjectives
• Parallelism
• Prepositional Phrase
• Past Simple Tense
• Past Continuous Tense
• Past Perfect Tense
• Past Progressive Tense
• Present Simple Tense
• Present Perfect Tense
• Personal Pronoun
• Personification
• Persuasive Writing
• Parallel Structure
• Phrasal Verb
• Predicate Adjective
• Predicate Nominative
• Phonetic Language
• Plural Noun
• Punctuation
• Punctuation Marks
• Preposition
• Preposition of Place
• Parts of Speech
• Possessive Adjective
• Possessive Determiner
• Possessive Case
• Possessive Noun
• Proper Adjective
• Proper Noun
• Present Participle
• Quotation Marks
• Relative Pronoun
• Reflexive Pronoun
• Reciprocal Pronoun
• Subordinating Conjunction
• Simple Future Tense
• Stative Verb
• Subjunctive
• Subject Complement
• Subject of a Sentence
• Sentence Variety
• Second Conditional
• Superlative Adjective
• Slash Symbol
• Topic Sentence
• Types of Nouns
• Types of Sentences
• Uncountable Noun
• Vowels and Consonants

Popular lessons

Stay awhile. Your weekly dose of grammar and English fun.

The world's best online resource for learning English. Understand words, phrases, slang terms, and all other variations of the English language.

• Abbreviations
• Editorial Policy

Have a language expert improve your writing

Run a free plagiarism check in 10 minutes, automatically generate references for free.

• Knowledge Base
• Methodology
• How to Write a Strong Hypothesis | Guide & Examples

How to Write a Strong Hypothesis | Guide & Examples

Published on 6 May 2022 by Shona McCombes .

A hypothesis is a statement that can be tested by scientific research. If you want to test a relationship between two or more variables, you need to write hypotheses before you start your experiment or data collection.

Table of contents

What is a hypothesis, developing a hypothesis (with example), hypothesis examples, frequently asked questions about writing hypotheses.

A hypothesis states your predictions about what your research will find. It is a tentative answer to your research question that has not yet been tested. For some research projects, you might have to write several hypotheses that address different aspects of your research question.

A hypothesis is not just a guess – it should be based on existing theories and knowledge. It also has to be testable, which means you can support or refute it through scientific research methods (such as experiments, observations, and statistical analysis of data).

Variables in hypotheses

Hypotheses propose a relationship between two or more variables . An independent variable is something the researcher changes or controls. A dependent variable is something the researcher observes and measures.

In this example, the independent variable is exposure to the sun – the assumed cause . The dependent variable is the level of happiness – the assumed effect .

Prevent plagiarism, run a free check.

Step 1: ask a question.

Writing a hypothesis begins with a research question that you want to answer. The question should be focused, specific, and researchable within the constraints of your project.

Step 2: Do some preliminary research

Your initial answer to the question should be based on what is already known about the topic. Look for theories and previous studies to help you form educated assumptions about what your research will find.

At this stage, you might construct a conceptual framework to identify which variables you will study and what you think the relationships are between them. Sometimes, you’ll have to operationalise more complex constructs.

Step 3: Formulate your hypothesis

Now you should have some idea of what you expect to find. Write your initial answer to the question in a clear, concise sentence.

Step 4: Refine your hypothesis

You need to make sure your hypothesis is specific and testable. There are various ways of phrasing a hypothesis, but all the terms you use should have clear definitions, and the hypothesis should contain:

• The relevant variables
• The specific group being studied
• The predicted outcome of the experiment or analysis

Step 5: Phrase your hypothesis in three ways

To identify the variables, you can write a simple prediction in if … then form. The first part of the sentence states the independent variable and the second part states the dependent variable.

In academic research, hypotheses are more commonly phrased in terms of correlations or effects, where you directly state the predicted relationship between variables.

If you are comparing two groups, the hypothesis can state what difference you expect to find between them.

Step 6. Write a null hypothesis

If your research involves statistical hypothesis testing , you will also have to write a null hypothesis. The null hypothesis is the default position that there is no association between the variables. The null hypothesis is written as H 0 , while the alternative hypothesis is H 1 or H a .

Hypothesis testing is a formal procedure for investigating our ideas about the world using statistics. It is used by scientists to test specific predictions, called hypotheses , by calculating how likely it is that a pattern or relationship between variables could have arisen by chance.

A hypothesis is not just a guess. It should be based on existing theories and knowledge. It also has to be testable, which means you can support or refute it through scientific research methods (such as experiments, observations, and statistical analysis of data).

A research hypothesis is your proposed answer to your research question. The research hypothesis usually includes an explanation (‘ x affects y because …’).

A statistical hypothesis, on the other hand, is a mathematical statement about a population parameter. Statistical hypotheses always come in pairs: the null and alternative hypotheses. In a well-designed study , the statistical hypotheses correspond logically to the research hypothesis.

Cite this Scribbr article

If you want to cite this source, you can copy and paste the citation or click the ‘Cite this Scribbr article’ button to automatically add the citation to our free Reference Generator.

McCombes, S. (2022, May 06). How to Write a Strong Hypothesis | Guide & Examples. Scribbr. Retrieved 27 May 2024, from https://www.scribbr.co.uk/research-methods/hypothesis-writing/

Is this article helpful?

Shona McCombes

Other students also liked, operationalisation | a guide with examples, pros & cons, what is a conceptual framework | tips & examples, a quick guide to experimental design | 5 steps & examples.

bottom_desktop desktop:[300x250]

To support our work, we invite you to accept cookies or to subscribe.

You have chosen not to accept cookies when visiting our site.

The content available on our site is the result of the daily efforts of our editors. They all work towards a single goal: to provide you with rich, high-quality content. All this is possible thanks to the income generated by advertising and subscriptions.

By giving your consent or subscribing, you are supporting the work of our editorial team and ensuring the long-term future of our site.

If you already have purchased a subscription, please log in

How to use "hypothesis" in a sentence?

These sentences come from external sources and may not be accurate. bab.la is not responsible for their content.

• open_in_new Link to source
• warning Request revision

CULTURE & TRAVEL

Search for translations, search by language, social login.

Questions about example sentences with, and the definition and usage of "Hypothesis"

• Meanings of words and phrases
• Example sentences
• Similar words
• Translations
• Other types of questions

The meaning of "Hypothesis" in various phrases and sentences

Example sentences using "hypothesis", synonyms of "hypothesis" and their differences, translations of "hypothesis", other questions about "hypothesis", meanings and usages of similar words and phrases, latest words.

HiNative is a platform for users to exchange their knowledge about different languages and cultures.

• is it "soaked" adjective only referring to water? I could it be used for "sweat" for someone was ...
• How do you say this in English (US)? 何もかも投げ出したくなるよ。
• Please help me with this question: Anna is one of the best singers here. ==> Among
• How do you say this in English (US)? 英語難しいから勉強したく無い。
• How do you say this in English (US)? 何を話せばいいの？
• What is the difference between Japanese people don't tend to raise their hands themselves. and Ja...
• Hi! I need a word to express bathing in satl in a spiritual context. Do I say "rock salt", "coars...
• What is the difference between what kind of food is it and what kind of food it is ?
• hi guys mi question is the next when someone is grumpy I use cranky instead of grumpy but which o...
• What is the difference between ㅐ, ㅒ and ㅔ, ㅖ ?
• “감사하겠습니다”and “감사드리겠습니다” 무슨 차이가 있어요?
• só possui esses batchim duplos: ㄹㄱ-ㅂㅅ-ㄴㅈ-ㄹㄱ-ㄹㅎ- ㄴㅎ-ㄹㅌ-ㄹㅁ-ㄹㅍ-ㄹㄱ- ㄹㄱ-ㄴㅎ-ㅂㅅ-ㄹㅁ-ㄹㅂ- ㄴㅈ-ㄱㅅ?
• What is the difference between estás tranquilo and eres tranquilo ?
• How do you say this in English (US)? Que estás haciendo

Hypothesis in a Sentence  🔊

Definition of Hypothesis

a proposed explanation or theory that is studied through scientific testing

Examples of Hypothesis in a sentence

The scientist’s hypothesis did not stand up, since research data was inconsistent with his guess.  🔊

Each student gave a hypothesis and theorized which plant would grow the tallest during the study.  🔊

A hypothesis was presented by the panel, giving a likely explanation for why the trial medicine didn’t seem to have much of an effect on the patients.  🔊

During the study, the researcher changed her hypothesis to a new assumption that fit with current data.  🔊

To confirm his hypothesis on why the dolphin wasn’t eating, the marine biologists did several tests over a week’s time.  🔊

Other words in the Opinion, Belief category:

Most Searched Words (with Video)

Voracious: In a Sentence

Verbose: In a Sentence

Vainglorious: In a Sentence

Pseudonym: In a Sentence

Propinquity: In a Sentence

Orotund: In a Sentence

Magnanimous: In a Sentence

Inquisitive: In a Sentence

Epoch: In a Sentence

Aberrant: In a Sentence

Apprehensive: In a Sentence

Obdurate: In a Sentence

Heresy: In a Sentence

Gambit: In a Sentence

Pneumonia: In a Sentence

Otiose: In a Sentence

Examples of “Hypothesis” In A Sentence

The hypothesis is a very important part of doing science and thinking carefully. It is like the strong supporting structure of a building for the process of research. A hypothesis is a clever guess or idea that can be tested to see if it is true or not. It helps us understand things or predict what might happen. In this article, we will look at many examples of ‘hypothesis’ in sentences .

Table of Contents

Sentences with Hypothesis

• Hypothesis : The sun rises in the east.
• They formulated a null hypothesis to compare against the alternative.
• We need to revise the original hypothesis .
• They discussed the hypothesis with colleagues in their field.
• They formulated competing hypotheses to compare and contrast the findings.
• The students generated multiple hypotheses for their investigation.
• The hypothesis was generated from observations.
• The hypothesis is the starting point of scientific investigation.
• The researchers tested the hypothesis using various methodologies.
• We need to investigate the hypothesis
• The hypothesis needs more evidence to be proven.
• The hypothesis was rejected due to flaws in the experimental design.
• They tested the hypothesis using computer simulations.
• The team tested the hypothesis using advanced technology.
• The hypothesis was derived from logical reasoning.
• They conducted surveys to gather data for their hypotheses .
• They proposed alternative hypotheses for further exploration.
• The hypothesis was consistent with data from other studies.
• The hypothesis was based on logical reasoning.
• The hypothesis was supported by the statistical analysis.

Sentences with “Hypothesis”

• The hypothesis was proven incorrect.
• The hypothesis was rejected due to lack of evidence.
• They discussed the hypothesis with their peers.
• The hypothesis was proposed based on logical deductions.
• The hypothesis was validated through rigorous peer review.
• The team discussed potential hypotheses during brainstorming sessions.
• They discussed the limitations of their hypothesis
• The students proposed various hypotheses for the investigation.
• The hypothesis was confirmed by independent replication studies.
• The students formed testable hypotheses for their projects.
• They used a control group to test their hypothesis .
• The hypothesis was formulated as a cause-and-effect relationship.
• The hypothesis was supported by the literature review.
• Scientists test their hypotheses through experiments.
• The hypothesis was proposed based on observations in nature.
• They analyzed the data to validate the hypothesis .
• They designed the experiment to test the hypothesis
• The hypothesis was based on previous research findings.
• They revised the hypothesis based on constructive feedback.
• They presented their hypotheses at a research symposium.
• They conducted experiments to test their hypotheses .
• The hypothesis was supported by a large and diverse sample.
• The researchers tested the hypothesis using a variety of methodologies.
• They conducted surveys to gather data that supported their hypothesis .
• The team formulated new hypotheses for future investigations.
• The hypothesis was consistent with experimental results.

“Hypothesis” Use in Sentence

• They discussed the implications of the hypothesis on their field.
• The researchers discussed the implications of their hypotheses .
• The hypothesis was derived from careful observation and analysis.
• The team developed alternative hypotheses for further investigation.
• They presented their hypotheses to the research community.
• The hypothesis was based on a comprehensive review of the literature.
• The hypothesis was supported by strong logical reasoning.
• They discussed the implications of their hypothesis for future research.
• The hypothesis was based on a well-established scientific theory.
• The researchers tested their hypotheses using different methodologies.
• The hypothesis was supported by empirical evidence.
• The researchers evaluated their hypotheses
• The hypothesis was disproven by contradictory evidence.
• The researchers discussed the limitations of their hypotheses .
• The hypothesis was based on a well-established theory.
• The hypothesis was supported by a large sample size.
• The hypothesis was consistent with patterns observed in nature.
• They proposed new hypotheses for future investigation.
• The hypothesis was confirmed by the results of the study.
• The hypothesis guided the research process.
• The hypothesis was supported by strong scientific consensus.
• The hypothesis was rejected due to methodological limitations.
• The researchers proposed several hypotheses to explain the phenomenon.
• The hypothesis was confirmed by multiple researchers in the field.
• The hypothesis was validated through multiple studies.

Sentences Using “Hypothesis”

• The researchers conducted experiments to test their hypotheses .
• The hypothesis was based on observations from nature.
• The hypothesis was supported by a wide range of evidence.
• They formed competing hypotheses to compare.
• Scientists often revise their hypotheses based on new data.
• They conducted experiments to support their hypotheses .
• The team discussed their hypothesis during the meeting.
• The students discussed their hypotheses in class.
• They developed a new hypothesis based on recent findings.
• They discussed the hypothesis with other experts in the field.
• The hypothesis was supported by a significant p-value.
• The hypothesis was generated from real-world observations.
• Mary’s hypothesis was supported by the data.
• They tested their hypotheses across different populations.
• The researchers tested multiple hypotheses to find the answer.
• They presented their hypothesis at a scientific conference.
• The hypothesis was supported by strong evidence.
• They presented their hypotheses in a clear and concise manner.
• The researchers proposed a working hypothesis to start their study.
• The team discussed the hypothesis during the brainstorming session.
• The researchers proposed different hypotheses for the observed behavior.
• The hypothesis is a crucial part of any scientific study.
• The hypothesis was refuted by the experimental results.

“Hypothesis” Sentences Examples

• We need to gather more data to test the hypothesis .
• The hypothesis was consistent with existing theories.
• The hypothesis was supported by a strong theoretical framework.
• The hypothesis was based on previous studies.
• They formulated a null hypothesis as the default assumption.
• The hypothesis was consistent with theoretical predictions.
• The hypothesis was based on prior knowledge.
• The hypothesis was supported by strong experimental data.
• The team formed a new hypothesis after analyzing the data.
• The hypothesis was consistent with the findings of previous studies.
• The hypothesis was rejected due to methodological flaws.
• The hypothesis was proven right after extensive testing.
• The hypothesis was consistent with real-world observations.
• The team tested their hypothesis in different conditions.
• The hypothesis was consistent with the predictions.
• The students generated their hypotheses for the experiment.
• The hypothesis was confirmed by multiple independent studies.
• The hypothesis was tested using a randomized controlled trial.
• They formulated a null hypothesis to compare against.
• The hypothesis was based on inductive reasoning.
• The hypothesis was validated through repeated experiments.
• The hypothesis guided the design of the experiment.
• They used statistical analysis to validate the hypothesis .
• The researchers discussed the implications of their hypothesis on society.
• They revised the hypothesis based on feedback from experts.
• The hypothesis was confirmed by expert analysis.
• Hypotheses are essential in the scientific method.
• Lisa proposed an interesting hypothesis for her project.
• They analyzed the data to support their hypothesis .
• The hypothesis was supported by compelling arguments.
• They conducted interviews to explore their hypotheses .

Use “Hypothesis” In A Sentence

• Sarah formulated a new hypothesis for her research.
• The hypothesis was confirmed by the experiment.
• The hypothesis was generated from prior observations.
• They conducted surveys to test their hypotheses .
• The hypothesis was supported by well-documented experimental results.
• The hypothesis was supported by strong correlations.
• The hypothesis was proposed after reviewing the literature.
• They proposed a working hypothesis to guide their study.
• The hypothesis was consistent with the observed results.
• They proposed alternative hypotheses for future exploration.
• The hypothesis was validated through rigorous statistical methods.
• The researchers tested their hypotheses
• John’s hypothesis led to groundbreaking discoveries.
• The hypothesis was supported by statistical significance.
• The researchers formulated a null hypothesis to compare against.
• The hypothesis was supported by theoretical predictions.
• They formed competing hypotheses to compare and contrast.
• The hypothesis was consistent with historical data.
• The hypothesis was supported by multiple lines of evidence.
• The hypothesis was revised based on feedback from reviewers.
• The scientists formulated a specific hypothesis to test.
• The hypothesis was based on empirical data.

Use Adaptable In A Sentence

Manifestation in a sentence

Sentences with Effective

Daily Routine Sentences in English

Hypothesis In A Sentence | Images

Related Posts

Types of sentences with examples

100 Short English Sentences Used in Daily Life

Conversation Simple English Sentences For Daily Use

Leave a comment cancel reply.

Your email address will not be published. Required fields are marked *

Save my name, email, and website in this browser for the next time I comment.

Hypothesis used in a sentence

Hypothesis in a sentence as a noun.

... My hypothesis is there's a payoff racket going on.

There is no evidence for the hygiene hypothesis.

Oftentimes I'll just grab 4000 or so machines and run a MapReduce to test out some hypothesis.

When I was starting my company, I had to cold-call a few dozen people to test a hypothesis.

"Whether or not you believe his hypothesis, you cannot deny that he is not rigorously testing it.

[...] One commonly used hypothesis to explain the effect of Stockholm syndrome is based on Freudian theory.

"If we use gradual engagement, we will have more, higher quality signups" is a testable hypothesis.

In a world where reality itself is relative and subject to social proof, there is no need to double check your facts or to prove the null hypothesis.

If merely being exposed to a hypothesis you disagree with offends you, then I don't understand how you can ever hope to have a meaningful debate.

My hypothesis is that we need to reform the representation of programs to address this use case: I download the sources for a tool I use, wanting to make a tweak.

Climate science is about gathering data, putting forth a testable hypothesis and seeing how future data fits the prediction.

Interesting hypothesis, and he makes it look very scientific with the formulae and all, but it's still a wild crazy guess that delivers no actual falsifiable prediction.

[1] I mean, I know that's how science is supposed to work, but in these days of politicized everything it's cool to see someone say "new data disproves my previous hypothesis" and continue working to find the real truth.

"One way to confirm or deny this hypothesis would be to look at companies that previously were high-performing, and then see what the correlation between CEO pay and the change in market performance is within that group.

Those who want to intentionally attract media attention should present themselves as such, instead of pretending to be doing any kind of meaningful experiment and hypothesis testing.

This Economist post[0] addresses some of the many comments about statistical outliers:> The big surprise has been the support for the unabashedly elitist “super-forecaster” hypothesis.

The autoimmune hypothesis is yet another autism hypothesis that is advanced primarily by parents, because it offers more hope than a neurological etiology.

First, before you even start trying to get a meeting, these 2 things must both be true:• You have a strong hypothesis of what Company X’s specific pain point is, informed by research• If your hypothesis is right, there is a >50% chance that your product can actually solve their pain pointIf both of the above are not true, do not proceed.

Hypothesis definitions

a proposal intended to explain certain facts or observations

a tentative insight into the natural world; a concept that is not yet verified but that if true would explain certain facts or phenomena; "a scientific hypothesis that survives experimental testing becomes a scientific theory"; "he proposed a fresh theory of alkalis that later was accepted in chemical practices"

See also: possibility theory

a message expressing an opinion based on incomplete evidence

See also: guess conjecture supposition surmise surmisal speculation

• Top1000 word
• Top5000 word
• Conjunction
• Sentence into pic

Hypothesis in a sentence

• 某某   2016-01-13 联网相关的政策
• improvement  (238+32)
• on balance  (53)
• wicked  (168+7)
• handlebar  (25)
• rainy  (165+9)
• trudge  (41+1)
• checkpoint  (102)
• events  (166+80)
• courage  (289+31)
• blizzard  (120+5)
• weary  (158+11)
• rationalize  (57+1)
• refund  (173+13)
• pack up  (56)
• at dusk  (69+1)
• university  (168+75)
• outdoors  (157+12)
• be concerned about  (42)
• on one's own  (38)
• aristocrat  (50)

What happens if Trump is convicted in New York? No one can really say

W hen the judge overseeing Donald Trump's criminal trial found on May 6 that Trump had violated a gag order for a 10th time, he told him that "the last thing I want to do is to put you in jail."

"You are the former president of the United States and possibly the next president , as well," said Justice Juan Merchan, reflecting on the momentous weight of such a decision.

Whether to jail the Republican Party's presumptive nominee for president is a choice that Merchan may soon face again, if jurors in Trump's "hush money" case vote to convict him . Closing arguments began Monday , with jury deliberations to follow.

What exactly would happen if the jury finds Trump guilty is difficult to predict. Trump is being tried in New York state court, where judges have broad authority to determine when sentences are handed down after convictions and what exactly they will be, according to former Manhattan prosecutor Duncan Levin. That differs from federal court, where there's typically a waiting period between a conviction and sentencing. 

"It's much more informally done in state court. I've had cases where the jury comes back and says, 'guilty,' and the judge thanks the jury, and excuses them, and says, 'Let's sentence the defendant right now," said Levin. "Obviously, everything's a little different about this case than the typical case."

Each of the 34 felony falsification of business records charges that Trump is facing carries a sentence of up to four years in prison and a $5,000 fine. He has pleaded not guilty.

Norm Eisen, an author and attorney, recently analyzed dozens of cases brought by the Manhattan District Attorney's Office in which falsifying business records was the most serious charge at arraignment. He found that roughly one in 10 of those cases resulted in a sentence of incarceration. But he also cautioned that those prosecutions often involved other charges and noted the dynamics at play in Trump's case make his sentence particularly hard to forecast.

If Trump is found guilty, Merchan would have fairly wide leeway in determining a punishment, including sentencing Trump to probation or house arrest.

Levin said the option of confining Trump to his home, followed by a period on probation, might be appealing to Merchan, who has repeatedly indicated he's concerned about limiting a presidential candidate's ability to speak freely. Such an option would allow Trump to do interviews and access social media from his home.

From the day Trump was first arraigned , on April 4, 2023, Merchan has said he was loath to interfere with Trump's ability to campaign.

"He is a candidate for the presidency of the United States. So, those First Amendment rights are critically important, obviously," Merchan said that day.

And on May 6, he opined more broadly on the additional people who would be burdened by jailing Trump.

Merchan called incarceration "truly a last resort for me," saying, "I also worry about the people who would have to execute that sanction: the court officers, the correction officers, the Secret Service detail, among others."

Still, that day, he cautioned Trump that jail is not out of the question.

"I want you to understand that I will, if necessary and appropriate," Merchan said.

It's a possibility that officials in state and federal agencies have begun preparing for, according to a New York corrections source, who said the Secret Service has met with local jail officials. As a former president, Trump is entitled to Secret Service protection for the rest of his life, wherever he happens to be. Behind bars, corrections officers would in turn be responsible for protecting those agents assigned to Trump.

Where Trump might serve any jail or prison sentence is one of many factors that remains up in the air. Shorter sentences can be served at the city's Rikers Island Jail Complex, which has two wings that are typically used for high-profile or infamous inmates. (Neither, of course, has ever held someone who comes with his own security detail.)

Officials must have a plan in place, just in case, said Levin.

"He could be remanded on the spot," Levin said.

Katrina Kaufman contributed reporting.

Why is immunotheraphy not being used as a tool in the war against Alzheimer's Disease?

3-minute read.

Editor's note: Alexander Roberts is a longtime contributor to lohud.com, The Journal News and the USA TODAY Network. This is the first of a regular, monthly series of columns titled The Roberts Report.

Are drug companies delaying a potential cure for Alzheimer’s Disease?

The most powerful weapon against disease is not a drug. It is the body’s own immune system that constantly senses and neutralizes a huge variety of external and internal threats, from pathogens to abnormal cells. Dr. James Allison, together with Dr. Tasuku Honjo, received the 2018 Nobel Prize in Medicine for demonstrating that boosting the body’s systemic immune system could fight cancer.  Their research launched an explosion of life-saving immunotherapies that can treat formerly incurable cancers.

Curiously, the immunotherapy revolution has bypassed age-related neurodegenerative diseases like Alzheimer’s. Critics blame two factors: the stubborn myth that the blood- brain barrier prevents the immune system from operating in the brain, and a 25-year preoccupation--some would say obsession--with an Alzheimer’s treatment that has yielded minimal results.

Challenging the immune system’s lack of brain access

The myth of the immune system’s lack of access to the brain was debunked 25 years ago by a professor of neuroimmunology and her team at the Weizmann Institute of Science in Israel. Professor Michal Schwartz felt it made no sense that the blood’s cell repair system would be off limits to one of its most critical organs. She successfully challenged the myth with seminal discoveries that immune cells are guardians of the brain, needed for life-long brain maintenance and repair. Schwartz is recognized as one of the world’s foremost neuroimmunologists, receiving the Israel Prize, that nation’s highest honor for life sciences, and was listed last year in Forbes among the top 50 most influential women in science and technology.

How it works

After establishing the immune system operates in the brain, Schwartz set out to prove that the breakthrough drugs that jumpstart the body’s immune system to fight cancer could be modified to fight Alzheimer’s and other dementias.

When the immune system is overwhelmed or exhausted, switches in the blood called “checkpoints” that turn immune response on and off become stuck on “off.” The antibodies used by oncologists are directed to the checkpoints. They disable the checkpoint inhibitor proteins to get the T cells working again. By 2016, in experiments on mice that modeled Alzheimer’s Disease, Schwartz’s team used modified checkpoint antibodies to rejuvenate the immune system in the brain. They were able to arrest, and even reverse cognitive decline. The benefit did not depend on whether the Alzheimer’s was early or late stage. Mice ravaged by Alzheimer’s showed improved cognition and could navigate mazes from their youth.

Galvanized by those achievements, the Israeli scientist embarked on developing and testing an immune checkpoint inhibitor therapy for Alzheimer’s. She again encountered a roadblock.

The amyloid hypothesis

Schwartz began testing her understanding of the brain’s immune system amid ongoing attempts by numerous companies to develop a treatment that targets the accumulated Beta-amyloid and Beta-amyloid plaques associated with the brains of Alzheimer patients. It’s called the Amyloid Hypothesis that Beta-amyloid deposits cause Alzheimer’s. Beta-amyloid is a sticky protein known to interfere in the work of synapses and neurons. Despite disappointing results and over 20 anti-amyloid drugs that failed in clinical trials, the hypothesis persists.  A 2019 article by Sharon Begley in the magazine STAT noted:

“The most influential researchers have long believed so dogmatically in one theory of Alzheimer’s that they systematically thwarted alternative approaches. Several scientists described those who controlled the Alzheimer’s agenda as a ‘cabal’.”

The FDA approves an anti-amyloid drug

Begley, an award-winning science writer whose resume included science columnist at the Wall Street Journal and science editor at Newsweek unfortunately did not live to see the excitement followed by controversy that erupted over the release of Aduhelm (aducanumab) by Biogen, the first drug shown to slow the disease by removing amyloid plaques.

That drug’s approval in June 2021 occurred over the objections of an advisory council of 15 senior FDA officials who cited weak clinical evidence of effectiveness and serious side effects. In a statement at the time, a former Biogen senior medical director who designed the late-stage clinical trials, Dr. Vissia Viglietta said, “This approval shouldn’t have happened. It defeats everything I believe in scientifically and it lowers the rigor of regulatory bodies.”

Biogen announced in January of this year it was discontinuing the drug.

Like Aduhelm, the only other approved drug for Alzheimer’s, Leqembi (lecanemab), must be taken very early by patients with mild cognitive impairment or mild dementia, when they can still function independently. Also based on removing amyloid plaques, Leqembi won’t improve cognition or halt progression of the disease, much less cure it. The drug slowed progression about 4 ½ months during the 18-month clinical trial compared to placebo. After the initial disease stages, Leqembi provides no benefit compared to placebo. 

In March, the FDA was set to approve a third anti-amyloid drug, this one developed by Ely Lilly called donanemab.  It had slightly better results in clinical trials, but its March approval was unexpectedly delayed by the FDA, pending an independent advisory committee review.

A new market for the Amyloid Hypothesis

Despite the modest results of their anti-amyloid medications, which all have serious side effects, such as brain swelling and in rare cases death, the drug companies are doubling down on the Amyloid Hypothesis. Clinical trials at Eli Lilly will purportedly suggest that donanemab should be taken by all non-cognitively impaired individuals with evidence of amyloid plaques. This despite studies indicating 30%-50% of elderly people (mean age of 85) have such plaques and will never suffer symptoms.

Research on immune checkpoint inhibitors for Alzheimer’s

With help from the Weizmann Institute, Schwartz founded ImmunoBrain Checkpoint , a clinical-stage biopharmaceutical company testing a new antibody specific to immune checkpoints called Aboo2. Tailored to treat Alzheimer’s disease, it blocks a checkpoint protein called PD-L1. According to a company spokesman, “Ab002 is the ONLY therapeutic agent in development for AD with preclinical data suggesting simultaneous therapeutic effects on Amyloid pathology, Tau pathology [another toxic protein associated with Alzheimer’s] and neuroinflammation.”

ImmunoBrain Checkpoint is now conducting a Phase 1 clinical trial with Alzheimer’s patients in the U.K., Europe and Israel. Based on a preclinical study, Schwartz says Aboo2 has a significantly lower potential for side effects compared to antibodies used in cancer therapies. 

The company’s approach recently attracted significant support with a $5 million grant from the National Institute on Aging, a division of the National Institutes of Health, and $1 million from the Alzheimer’s Association.

According to Alzheimer’s Association media director Niles Frantz, “Providing a $1 million research grant clearly demonstrates that we believe the area of research shows promise. Many of the research projects funded by the Alzheimer's Association generate significant new and compelling data, which enables the researcher(s) to secure additional funding to extend the time and/or expand the scope of their work.”

With the cost of bringing a drug to market at $1 billion, companies like ImmunoBrain need a major pharmaceutical firm to back it, which would require a willingness to consider alternatives to the Amyloid Hypothesis.

More from Alexander Roberts: The anxiety epidemic:  A manufactured crisis

The human cost of Alzheimer’s Disease

Christa Daniello has worked with Alzheimer’s patients for over 25 years at The Osborn Senior Living in Rye, New York, where she is a vice president, and said the cost of the disease is significant.

“You never forget it when the wife and children of a 65-year-old Harvard graduate stand before you crying, with a husband and father who no longer recognizes them. It’s heart-breaking and it’s time for the drug companies to try a different approach.”

Alexander Roberts is a former New York City television news reporter and founder and CEO emeritus of the nonprofit Community Housing Innovations, based in White Plains, New York.

More From Forbes

Figuring out the innermost secrets of generative ai has taken a valiant step forward.

• Share to Facebook
• Share to Twitter
• Share to Linkedin

Important steps in figuring out the inner sanctum within the core of generative AI are finally being ... [+] made.

In today’s column, I aim to provide an insightful look at a recent AI research study that garnered considerable media attention, suitably so. The study entailed once again a Holy Grail ambition of figuring out how generative AI is able to pull off being so amazingly fluent and conversational.

Here’s the deal.

Nobody can right now explain for sure the underlying logical and meaningful basis for generative AI being extraordinarily impressive. It is almost as though an awe-inspiring magical trick is taking place in front of our eyes, but no one can fully delineate exactly how the magic truly works. This is a conundrum, for sure.

Many AI researchers are avidly pursuing the ambitious dream of cracking the code, as it were and finding a means to sensibly interpret the massive mathematical and computational morass that underlies modern-day large-scale generative AI apps, see my coverage at the link here . They do so because they are intrigued by the incredible and vexing puzzle at hand. They do so to potentially gain fame or fortune. They do so since it is a grand challenge that once solved might bring forth other advances that we don’t yet realize await discovery. Lots of really good reasons exist for this arduous and at times frustrating pursuit.

I welcome you to the playing field and urge you to join in the hunt.

Headlines Galore With A Bit Of Moderation Needed

The recently released study that caused noteworthy interest was conducted by Anthropic, the maker of the generative AI app known as Claude. I will walk you through the ins and outs of the work. This will include excerpts to whet your appetite and include my analysis of what this all means.

Trump Trial Prosecutor Ends Closing Argument After Nearly 5 Hours—Jury Instructions Set For Wednesday

Gas explosion in downtown youngstown ohio injures at least 7, trump lashes out at robert de niro after actor calls him a ‘tyrant’ outside courthouse.

Here are some of the headlines that remarked on the significance of the study:

• “No One Truly Knows How AI Systems Work. A New Discovery Could Change That” (Time)
• “Here’s What’s Really Going On Inside An LLM’s Neural Network” (Ars Technica)
• “A.I.’s Black Boxes Just Got A Little Less Mysterious” (New York Times)
• “Anthropic Tricked Claude Into Thinking It Was The Golden Gate Bridge And Other Glimpses Into The Mysterious AI Brain)” (VentureBeat)

There is little doubt that this latest research deserves rapt attention.

I might also add that the AI community all told is steadily biting off just a tiny bit at a time concerning what makes generative AI symbolically tick. There is no assurance that our hunting is heading in the right direction. Maybe we are finding valuable tidbits that will ultimately break the inner mysteries. On the other hand, it could be that we are merely chewing around the edges and remain far afield from solving what is undoubtedly a great mystery.

Time will tell.

As we proceed herein, I will make sure to properly introduce you to the terminology that underscores efforts to unpack the mechanisms of generative AI. If you were to dive into these matters headfirst you would discover that a slew of weighty vocabulary is being utilized.

No worries, I’ll make sure to explain the particulars to you.

Hang in there and we will get to covering these vocabulary gems of the AI field:

• Generative AI (GenAI, gAI)
• Large Language Models (LLMs)
• Mechanistic interpretability (MI)
• Artificial neural networks (ANNs)
• Artificial neurons (ANs)
• Monosemanticity
• Sparse autoencoders (SAE)
• Scaling laws
• Linear representation hypothesis
• Superposition hypothesis
• Dictionary learning
• Features as computational intermediates
• Features neighborhoods
• Feature completeness
• Safety-relevant features
• Features manipulations

In my ongoing column, I’ve mindfully examined other similar research studies that have earnestly sought to unlock what is happening inside generative AI. You might find of special interest this coverage at the link here and this posting at the link here . Take a look at those if you’d like to go further into the brass tacks of a fascinating and fundamental journey that is abundantly underway.

A quick comment before we leap into the fray.

Readers of my column are well aware that I eschew the ongoing misuse of wording in and around the AI arena that tries to attach human-based characteristics to today’s AI. For example, some have referred to the study that I am about to explore as having delved into the “mind” of AI or showcased the AI “brain”. Those are exasperatingly misapplied wordings. They are insidiously anthropophilic and falsely mislead people into believing that contemporary AI and humans are of the same ilk.

Please don’t fall for that type of wording.

You will hopefully observe that I try my best to avoid making use of those comparisons. I want to emphasize that we do not today have any sentient AI. Period, end of story. That might be a surprise since there is a lot of loose talk that suggests otherwise. For my detailed coverage of such matters, see the link here .

Anyway, sorry about the soapbox speech but I try to deter the rising tide of misleading characterizations whenever I get the chance to do so.

On with the show.

Trying To Get The Inner Mechanisms Figured Out

Let’s start at the beginning.

I assume you’ve used a generative AI app such as ChatGPT, GPT-4, Gemini, Bard, Claude, or the like. These are also known as large language models (LLMs) due to the aspect that they model natural languages such as English and tend to be very large-scale models that encompass a large swatch of how we use our natural languages. They are all pretty easy to use. You enter a prompt that contains your question or issue that you want solved. Upon hitting return, the AI app generates a response. You can then engage in a series of prompts and responses, acting as though you are carrying out a conversation.

Easy-peasy.

How does the generative AI app or LLM craft the responses?

In one sense, the answer is very straightforward.

The prompt that you enter is converted into a numeric format commonly referred to as tokens (see my in-depth explanation at the link here ). The numeric version of your entered words is then funneled through an elaborate maze of mathematical and computational calculations. Eventually, a response is generated, still in a numeric or tokens format, and converted back into words so that you read what it says. Voila, you then see the words displayed that were derived as a response to your entered prompt.

If we wanted to do so, it would be quite possible to follow the numbers as they weave through the mathematical and computational maze. This number would lead to that number. That number would lead to this other number. On and on this would go. It would be a rather tedious tracing of thousands upon thousands, or more like millions upon millions of numbers crisscrossing here and there.

Would a close examination of the numbers tell you what is conceptually or symbolically happening within the mathematical and computational maze?

Strictly speaking, perhaps not. It would just seem like a whole bunch of numbers. You would be hard-pressed to say anything other than that a number led to another number, and so on. Explaining how that made a difference in getting a logical or meaningful answer to your prompt would be extraordinarily difficult.

One possibility is that there isn’t any meaningful way to express the vast series of arcane calculations. Suppose that it all happens in a manner beyond our ability to understand what the underlying mathematical and computational mechanics are conceptually doing. Just be happy that it works, some might insist. We don’t need to know why, they would say.

The trouble with this is that we are increasingly finding ourselves reliant on so-called black boxes that are modern-day generative AI.

If you can’t logically or meaningfully explain how it generates responses, this ought to send chills up our spines. We have no systematic means of making sure it is doing the right thing, depending upon what is meant by doing things right. The whole concoction might go awry. It might be waylaid by evildoers, see my discussion at the link here . All manners of concern arise when we are fully dependent upon a mysterious black box that remains inscrutable to coherent explanation.

I took you through that indication to highlight that we can at least inspect the flow of numbers. One might argue that a true black box won’t let you see inside. You customarily cannot peer into a presumed black box. In the case of generative AI, it isn’t quite the proper definition of a black box. We can readily see the numbers and watch as they go back and forth.

Take a moment and mull this over.

We can watch the numbers as they proceed throughout the input-to-output processing within generative AI. We also know the data structures that are used, and we know the formulas implemented as mathematical and computational calculators. The thing we don’t know and cannot yet explain is why in a conceptual symbolic sense the outputs turn out to be strikingly fitting to the words that we input.

How can we crack open this enigma?

Much of the AI research on this beguiling topic tends to explore smaller versions of contemporary generative AI. It is a classic move of trying to get our feet wet before diving into the entire lake. The cost to play around is a lot lower on a small version of generative AI. You can also more readily observe what is happening. All in all, starting in the small is handy.

I’ve discussed the prevailing discoveries from the small-scale explorations, see the link here .

Sometimes you need to take baby steps. Begin by crawling, then standing up and stumbling, then outright walking, and hope that you’ll one day be running and sprinting. The concern raised is that what we learn from small-scale explorations might not give rise to medium-scale and large-scale explorations.

That’s a strident belief by some that size matters. If a small-sized generative AI can be mapped and explained, one viewpoint is that this doesn’t directly imply that anything larger in size can be equally explained. Perhaps there is something else that happens when the scale increases. It could be that the seemingly toy-like facets of a small-scale generative AI do not ratchet up to the big-time versions.

Okay, the gist is that with generative AI we are faced with a kind of black box that we thankfully can inspect and are presented with the issue that the large scale makes it harder and costlier to do investigations, but we can at least do our best on the smaller scale versions.

I believe you are now up-to-speed, and I can get underway with examining the recent study undertaken and posted by Anthropic.

Fasten your seat belts for an exciting ride.

Examining Generative AI At Scale

I’ll first explore an online posting entitled “Mapping the Mind of a Large Language Model” by Anthropic, posted online on May 21, 2024. There is also an accompanying online paper that I’ll get to afterward and provides deeper details. Both are worth reading.

Here are some key points from the “Mapping the Mind of a Large Language Model” posting (excerpts):

• “Today we report a significant advance in understanding the inner workings of AI models. We have identified how millions of concepts are represented inside Claude Sonnet, one of our deployed large language models. “
• “This is the first-ever detailed look inside a modern, production-grade large language model.”
• “Opening the black box doesn't necessarily help: the internal state of the model—what the model is "thinking" before writing its response—consists of a long list of numbers ("neuron activations") without a clear meaning.”
• “From interacting with a model like Claude, it's clear that it’s able to understand and wield a wide range of concepts—but we can't discern them from looking directly at neurons. It turns out that each concept is represented across many neurons, and each neuron is involved in representing many concepts.”

Allow me a moment to reflect on those points.

Before I discuss the points, I would like to say that I was saddened and disappointed at the title wording of the posting, namely “Mapping the Mind of a Large Language Model”. Can you guess why I had some heartburn?

Yes, you probably guessed that the use of the word “Mind” was lamentedly an anthropomorphic reference. I realize that in this world of seeking eyeballs, it makes for more enthralling and catchy wording. There is plenty of that these days. You will note that in one of the bullets they at least put a somewhat similar word in quotes, i.e., “thinking”, which helps somewhat to avoid an anthropomorphizing indication.

Back to the bullet points. The researchers opted to use their prior work on examining small-scale generative AI or LLM to see what they could find when using a larger-scale variant. They point out that the sea of numbers does not readily lend itself to a human-level understanding of what is meaningfully and symbolically taking place.

They mention “neurons” and such aspects as “neuron activations”.

Let me bring you into the fold.

Generative AI and LLMs tend to be designed and programmed by using mathematical and computational techniques and methods known as artificial neural networks (ANNs).

The idea for this is inspired by the human brain consisting of real neurons biochemically wired together into a complex network within our noggins. I want to loudly clarify that how artificial neural networks work is not at all akin to the true complexities of so-called wetware or the human brain, the real neurons, and the real neural networks.

Artificial neural networks are a tremendous simplification of the real things. It is at best a modicum of a computational simulation. Indeed, various aspects of artificial neural networks are not viably comparable to what happens in a real neural network. ANNs can somewhat be used to try and simulate some limited aspects of real neural networks, but at this time they are a far cry from what our brains do.

In that sense, we are once again faced with a disconcerting wording issue. When people read or hear that a computer system is using “neurons” and doing “neuron activation” they would make the reasoned leap of faith that the computer is acting exactly like our brains do. Wrong. This is more of that anthropomorphizing going on.

The dilemma for those of us in AI is that the entire field of study devoted to ANNs makes use of the same language as is used for the biological side of the neurosciences. This is certainly sensible since the inspiration for the mathematical and computational formulation is based on those facets. Plus, the hope is that someday ANNs will indeed match the real things, allowing us to fully emulate or simulate the human brain. Exciting times!

Here's what I try to do.

When I refer to ANNs and their components, I aim to use the word “artificial” in whatever related wording I use. For example, I would say “artificial neurons” when I am referring to the inspired mathematical and computational mechanisms. I would say “neurons” when referring to the biological kinds. This ends up requiring a lot of repeated uses of the word “artificial” when discussing ANNs, which some people find annoying, but I think it is worth the price to emphasize that artificial neurons are not the same today as true neurons.

You can envision that an artificial neuron is like a mathematical function that you learned in school. An artificial neuron is a mathematical function implemented computationally that takes an input and produces an output, numerically so. We can implement that mathematical function via a computer system, either as software and/or hardware (with both working hand-in-hand).

I also speak of “artificial neural activations” as those artificial neurons that upon being presented with a numeric value as an input will then perform some kind of calculation and produce an output value. The function is said to have been activated or enacted.

Not everyone abides by that convention of strictly saying “artificial” when referring to the various elements of ANNs. They assume that the reader understands that within the context of discussing generative AI and LLMs, the notion of neurons and neuron activation refers to artificial neurons and artificial neuron activation. It is a shortcut that can be confusing to some, but otherwise silently understood by those immersed in the AI field.

I’ll leave it to you to decide which convention you prefer.

Moving Further Into The Forest

Let’s next see some additional salient points indicated in the notable research study (excerpts):

• “In October 2023, we reported success applying dictionary learning to a very small "toy" language model and found coherent features corresponding to concepts like uppercase text, DNA sequences, surnames in citations, nouns in mathematics, or function arguments in Python code.” (ibid).
• “Those concepts were intriguing—but the model really was very simple.” (ibid).
• “But we were optimistic that we could scale up the technique to the vastly larger AI language models now in regular use, and in doing so, learn a great deal about the features supporting their sophisticated behaviors.” (ibid).

Those points note that the prior work had found “features” that seemed to suggest concepts exist within the morass of the artificial neural networks used in generative AI and LLMs.

Let me say something about that.

Envision that we have a whole bunch of numerical mathematical functions. Lots and lots of them. We implement them on a computer via software. We connect them such that some feed their results into others. This is our artificial neural network, and each mathematical function is considered an artificial neuron.

This is the core of our generative AI app.

We will slap on a front end that takes words via a prompt from the user and converts those words into numbers or tokens. We feed those into the artificial neural network. Numbers flow from function to function, or we would say from artificial neuron to artificial neuron. When the calculations are completed, the numeric values are fed to our front end which converts them back into readable words.

I earlier asked you whether we could make any conceptual or symbolic sense out of all those numbers flowing back and forth.

Attempts so far have usually focused on looking at clumps of artificial neurons.

Perhaps if someone asks a question about the Golden Gate Bridge, for example, there might be some clump of artificial neurons within a vast array of them that are particularly activated using that reference. Voila, we might then claim that this or that set of artificial neurons seems to represent the conceptual notion and facets pertaining to references about the Golden Gate Bridge.

In smaller-scale generative AI, this has been a mainstay of results when trying to interpret what is going on inside the generative AI. There are various sets of artificial neurons in the overall artificial neural network used within the generative AI app that seem to signify specific words or phrases. I liken this to probing a messy interconnected contrivance of Christmas lights. You might do testing and see that if you plug in this or that plug, those lights here or there light up. When you plug in a different portion, this or that lights come on.

We can do the same with generative AI. Feed in particular words. Trace what parts of the artificial neural network seem to be producing notable values, or as said to be artificial neural activations. Try this repeatedly. If you consistently observe the same clump or set being activated, you might conclude that those represent the notion of whatever word or phrase is being fed in, such as referencing the Golden Gate Bridge.

You can further test out your hypothesis by instigating things.

Suppose we removed those artificial neurons from the ANN or maybe neutralized their functions so that they were now unresponsive. Presumably, the artificial neural network might no longer be able to respond when we enter our phrase of “Golden Gate Bridge”. Or, if it does respond, it might allow us to trace to some other part of the ANN that is apparently also involved in trying to mathematically and computationally model those particular words.

I trust that you are following along on this, and it makes reasonable sense, thanks.

If we examine an artificial neural network and discover portions that seem to represent particular words or phrases, what shall we overall call that specific set or subset of artificial neurons in a generic sense?

For the sake of discussion, let’s refer to those as “features”.

A feature will be an instance of our having found what we believe to be a portion of artificial neurons that seem to demonstrably represent particular words or phrases in our artificial neural network. In a sense, you could assert that a feature represents concepts , such as the concept of what a dog is, the concept of what the Golden Gate Bridge is, and so on.

Imagine it this way. We do lots of testing and discover a clump that seems to activate when we enter the word “dog” in a prompt. Perhaps this set of artificial neurons is a mathematical and computational modeling of the concept underlying what we mean by the use of the word “dog”. We find another clump that activates whenever we enter the word “cat” in a prompt. These are each a considered feature that we’ve managed to find within the overarching artificial neural network that sits at the core of our generative AI app.

How many “features” might there be in a large-scale generative AI app?

Gosh, that’s a tough question to answer.

In theory, there could be zillions of them. There might be a so-called “feature” that represents every distinct word in the dictionary. For the English language alone, there are about 150,000 or more words in an average dictionary. Add in phases. Add in all manner of permutations and combinations of how we use words. Make sure to place the words into the context of a sentence, the context of a paragraph, and the context of an entire story or essay.

Let’s see what the referenced research study had to say:

• “We mostly treat AI models as a black box: something goes in and a response comes out, and it's not clear why the model gave that particular response instead of another.” (ibid).
• “Opening the black box doesn't necessarily help: the internal state of the model—what the model is "thinking" before writing its response—consists of a long list of numbers ("neuron activations") without a clear meaning.” (ibid).
• “Previously, we made some progress matching patterns of neuron activations, called features, to human-interpretable concepts.”
• “Just as every English word in a dictionary is made by combining letters, and every sentence is made by combining words, every feature in an AI model is made by combining neurons, and every internal state is made by combining features.”

That pretty much echoes what I said above.

Features Are Not An Island Unto Themselves

There is a vital twist noted in the above last bullet point.

Features might rely upon or be considered related to other features.

Consider this. When I use the word “dog” there are a lot of interconnected concepts that we immediately tend to think about. You might at first think of a dog as an animal with four legs. Next, you might think about types of dogs such as golden retrievers. Next, you might consider dogs you’ve known such as your beloved pet from childhood. Next, you might consider famous dogs such as Lassie. Etc.

In the AI parlance, and within the context of generative AI and LLMs, let’s say that we might find “features” that relate to other features. I would dare say we would certainly expect this to be the case. It seems unlikely that one feature upon itself could represent everything about anything of any modest complexity.

I have led you step by step to the especially exciting part of the research study (excerpts):

• “We successfully extracted millions of features from the middle layer of Claude 3.0 Sonnet, (a member of our current, state-of-the-art model family, currently available on claude.ai), providing a rough conceptual map of its internal states halfway through its computation.” (ibid).
• “Whereas the features we found in the toy language model were rather superficial, the features we found in Sonnet have a depth, breadth, and abstraction reflecting Sonnet's advanced capabilities.” (ibid).
• “A feature sensitive to mentions of the Golden Gate Bridge fires on a range of model inputs, from English mentions of the name of the bridge to discussions in Japanese, Chinese, Greek, Vietnamese, Russian, and an image.” (ibid).
• “Looking near a ‘Golden Gate Bridge’ feature, we found features for Alcatraz Island, Ghirardelli Square, the Golden State Warriors, California Governor Gavin Newsom, the 1906 earthquake, and the San Francisco-set Alfred Hitchcock film Vertigo.” (ibid).

Those are fascinating and significant results.

Here’s why.

First, it seems that the notion of “features” as used when exploring smaller-scale generative AI was useful when exploring larger-scale generative AI. That is heartwarming and quite encouraging. Were this not the case, we might have to revert to step one and start over when trying to surface the inner facets of generative AI.

Second, the features in the large-scale generative AI were said to be deeper, wider, and have a greater semblance of abstraction. This again is something we would hope to see. Small-scale generative AI cannot usually make its way out of a paper bag, while large-scale generative AI provides all the knock-your-socks fluency that we experience. The base assumption is that large-scale generative AI achieves its loftiness via having a deeper, wider, and more robust abstraction of natural language than small-scale generative AI, by far. That seems to be the case.

Third, the researchers found not just a dozen or so features, not a few hundred features, not a few thousand features, but instead, they found millions of features. Great news. If they had only found a lesser number of features, it might suggest that features are extremely hard to find or that they cloak themselves in some unknown manner.

A problem that we might face is that there could be many, many millions upon millions of features. This is a problem since we then must figure out ways to find them, track them, and figure out what we might do with them. Anytime that you have something countable in the large, this presents challenges that will require further attention.

Never a dull moment in the AI field, I can assure you of that handy-dandy rule.

Safety Is A Momentous Part Of Deciphering Generative AI

What might we want to do with the features that we uncover within generative AI?

I suppose you could stare at them and admire them. Look at what we found, might be the proud exclamation.

A perhaps more utilitarian approach would be that we could do a better job at designing and building generative AI. Knowing about features would be instrumental in boosting what we can get generative AI to accomplish. Advances in AI are bound to arise by pursuing this line of inquiry.

There is a chance too that we might learn more about the nature of language and how we use language. Keep in mind that generative AI is a massive pattern-matching mechanism. To undertake the initial data training for generative AI, usually vast swaths of the Internet are scanned, trying to pattern match how humankind makes use of words.

Maybe there are new concepts that we’ve not yet landed on in real life. Now, hidden within generative AI, and yet to be found and showcased for all to see, we might discover eye-opening concepts that no one has heretofore voiced or considered. Wow, that would be something of grand amazement.

I have so far noted the upsides of finding features.

In life, and especially in the use case of AI, there is a duality of good and bad always at play. Generative AI can be used for the good of humanity. Hooray! Generative AI can also be used in underhanded ways and be harmful to humanity. That’s the badness associated with generative AI. I cover various examples of the dual use of generative AI at the link here .

Here’s what the research study indicated on the downsides or safety considerations (excerpts):

• “Importantly, we can also manipulate these features, artificially amplifying or suppressing them to see how Claude's responses change.” (ibid).
• “We also found a feature that activates when Claude reads a scam email (this presumably supports the model’s ability to recognize such emails and warn you not to respond to them).” (ibid).
• “Normally, if one asks Claude to generate a scam email, it will refuse to do so. But when we ask the same question with the feature artificially activated sufficiently strongly, this overcomes Claude's harmlessness training and it responds by drafting a scam email.” (ibid).
• “The fact that manipulating these features causes corresponding changes to behavior validates that they aren't just correlated with the presence of concepts in input text, but also causally shape the model's behavior. In other words, the features are likely to be a faithful part of how the model internally represents the world, and how it uses these representations in its behavior.” (ibid).
• “We hope that we and others can use these discoveries to make models safer.” (ibid).

The points above note that a feature that is supposed to suppress the AI from writing scam emails could be manipulated into taking the opposite stance and proffer the most scam of scam emails that one could compose.

Your gut reaction might be that this seems mildly disconcerting, but not overly dangerous or destructive.

Let me enlarge the scope.

Suppose we make use of generative AI for the control of robots, which is already being undertaken in an initial but rapidly growing manner, see my coverage at the link here . The generative AI has been carefully data-trained to be cautious around humans and not cause any injury or harm to people.

Along comes a hacker or evildoer. They manage to examine the inner workings of the generative AI and ferret out the feature that is indicative of being careful around humans. With a few light-touch changes, they get the feature to flip around and allow harm to humans. Going even further into this diabolical scheme, the feature is altered to purposely seek to harm people.

Yikes, you might be saying.

Stop right now on all this research that is identifying features. Drop it like a lead balloon. It is going to backfire on us. These efforts are going to be a goldmine for those who have evil intentions. We are handing them a roadmap to our destruction.

You have entered into the classic debate about whether knowledge can be too much of a good thing. The AI field has been grappling with this since the beginning of AI pursuits. A counterargument is that if we hide our heads in the sand, the odds are that those evildoers are going to ferret this out anyway. By putting this into the sunshine, hopefully, we have a greater chance of devising safety capabilities that will mitigate the underhanded plots.

On a related facet, I’ve been extensively covering the field of AI ethics and AI law, which dives deeply into these momentous societal and cultural questions, see the link here and the link here , for example. You are encouraged to actively participate in determining your future and the future of those generations yet to come along.

Getting Into Overtime On The Inner Mechanisms

I promised you at the start of this discussion that we would lean into a heaping of AI terminology.

Here’s that list again:

• And more...

The first items on the list have been generally covered so far. I introduced you to the nature of generative AI, large language models, artificial neural networks, and artificial neurons. The item on the list that refers to mechanistic interpretability is the AI insider phrasing for trying to interpret the inner mechanics of what is happening within generative AI. I’ve covered that too with you.

Some of the terms toward the tail-end of the list can be readily covered straightaway.

Specifically, let’s quickly tackle these:

You know now what a feature is, and the shortlist shown here augments various feature-related aspects.

You can seemingly realize that a feature could be construed as a computational intermediary . It is a means to an end. If someone enters a prompt that says, “How do I walk my dog”, the feature within generative AI that pertains to the word “dog” is a computational intermediary that will help with mathematically and computationally assessing that portion of the sentence and aid in generating a response.

Features can be considered within various potentially identifiable features-neighborhoods. There might be a feature that represents all four-legged creatures. The feature for “dog” would likely be within that neighborhood, as would the feature for “cat”. These are collections of features, and for which a given feature might well appear in more than one neighborhood and most likely does.

The completeness of a feature entails whether the feature covers a complete aspect or only a partial aspect. For example, maybe we discover a feature associated with “dog” but this feature does not account for hairless dogs. That’s in some other feature. We might then suggest that the feature we found is incomplete.

In the terminology that lists the phrase of safety-relevant features and feature manipulations, I already mentioned that we have to be on our toes when it comes to AI safety. You are already acquainted with that phraseology.

The list is now shortened to these fanciful terms:

I’d like to take you into the full paper that the researchers provided, allowing us to unpack those pieces of terminology accordingly.

The Deepness Of The Forest Can Be Astounding

I will be quoting from the paper entitled:

• “Scaling Monosemanticity: Extracting Interpretable Features From Claude 3 Sonnet” by Adly Templeton, Tom Conerly, Jonathan Marcus, Jack Lindsey, Trenton Bricken, Brian Chen, Adam Pearce, Craig Citro, Emmanuel Ameisen, Andy Jones, Hoagy Cunningham, Nicholas L Turner, Callum McDougall, Monte MacDiarmid, Alex Tamkin, Esin Durmus, Tristan Hume, Francesco Mosconi, C. Daniel Freeman, Theodore R. Sumers, Edward Rees, Joshua Batson, Adam Jermyn, Shan Carter, Chris Olah, and Tom Henighan, Anthropic , posted online May 21, 2024.

Let’s start with this (excerpts):

• “Our high-level goal in this work is to decompose the activations of a model (Claude 3 Sonnet) into more interpretable pieces.”
• “We do so by training a sparse autoencoder (SAE) on the model activations, as in our prior work and that of several other groups. SAEs are an instance of a family of ‘sparse dictionary learning’ algorithms that seek to decompose data into a weighted sum of sparsely active components.”
• “Our SAE consists of two layers.”
• “The first layer (‘encoder’) maps the activity to a higher-dimensional layer via a learned linear transformation followed by a ReLU nonlinearity. We refer to the units of this high-dimensional layer as “features.”
• “The second layer (‘decoder’) attempts to reconstruct the model activations via a linear transformation of the feature activations.”

That’s quite a mouthful.

I am going to explain this at a 30,000-foot level. I say that because I am going to take some liberties by simplifying what is otherwise a highly complex matter. For those trolls out there (you know who you are) that will be chagrined by the simplification, sorry about that, but if there is sufficient interest by readers, I will gladly come back around to this in a future posting and lay things out in more finite detail.

Unpacking initiated.

To try and find the features within generative AI, you could do so by hand. Go ahead and roll up those sleeves! That being said, you might as well get started immediately because to ferret out millions of them you would work by hand until the cows come home. It’s just not a practical approach when inspecting a large-scale generative AI app.

We need to devise a piece of software that will do the heavy lifting for us.

Turns out that there is a software capability known as a sparse autoencoder (SAE) that can be used for this very purpose. Thank goodness. You might find it of idle interest that an SAE is devised by using an artificial neural network. In that sense, we are going to use a tool that is based on ANN to try and ferret out the inner secrets of a large-scale ANN. Mind-bending. I discuss this further at the link here .

We can set up the SAE to examine a generative AI app when we are feeding prompts into it. Let the SAE find the various activations. This uses an underlying algorithm that is referred to as dictionary learning.

Dictionary learning essentially involves finding foundational pieces of something and then trying to build upon those toward a larger semblance, almost like examining LEGO blocks and then using those to build a structure such as a LEGO flower or LEGO house. Some AI researchers believe that dictionary learning is quite useful for this task, while others suggest that different methods might be more suitable. The jury is out on this for the moment.

Whew, go ahead and take a short break if you like, perhaps get a glass of wine. Congrats, you are halfway through this discourse on the heavy side of AI verbiage.

Let’s clock back in.

Monosemanticity is a word that frequently is used by linguists. It refers to the idea of having one meaning, wherein “mono” is of one thing and semanticity refers to the semantics of words. Some words are monosemnatic and have only one meaning, while other words are polysemantic and have more than one meaning. An example of a word that is polysemantic would be the word “bank”. If I toss the word “bank” at you and ask you what it means, you will indubitably scratch your head and probably ask me which meaning I intended. Did I mean the bank that is a financial institution, or did I mean the bank that is at the edge of a stream or river?

Features within generative AI are likely to involve some words that are monosemantic and others that are polysemantic. Usually, you can discern which meaning is coming into play by examining the associated context. When I tell you that I managed to climb up on the bank, I assume you would be thinking of a river or lake rather than your local ATM.

More Of This Complexity Enters Into The Big Picture

Let’s discuss scaling laws.

Here is a related excerpt from the cited paper:

• “Training SAEs on larger models is computationally intensive. It is important to understand (1) the extent to which additional compute improves dictionary learning results, and (2) how that compute should be allocated to obtain the highest-quality dictionary possible for a given computational budget.” (ibid).

The crux is that the running of the SAE is going to consume computer processing time. Someone has to pay for those processing cycles. We want to run the SAE as long as we can afford to do so, or at least until we believe that a desired number of features have been sufficiently found. Each feature we discover is going to cost us something in computer time used. Money, money, money.

A wise thing to do would be to try and get the most bang for our buck. No sense in having the SAE chew up valuable server time if it isn’t producing a wallop of nifty features. Scaling laws are basically rules of thumb that at some point you’ve probably done as much as you can profitably do. Going a mile more might not be especially fruitful.

This then leaves us with these last two pieces of hefty terminology to unravel:

Here are some especially relevant excerpts from the cited paper:

• “Our general approach to understanding Claude 3 Sonnet is based on the linear representation hypothesis and the superposition hypothesis.” (ibid).
• “At a high level, the linear representation hypothesis suggests that neural networks represent meaningful concepts – referred to as features – as directions in their activation spaces.” (ibid).
• “The superposition hypothesis accepts the idea of linear representations and further hypothesizes that neural networks use the existence of almost-orthogonal directions in high-dimensional spaces to represent more features than there are dimensions.” (ibid).

Tighten your belt for this.

Linear representation means that we can at times represent something of a complex nature via a somewhat simpler linear depiction. If you’ve ever taken a class in linear algebra, think about how you used various mathematical functions and numbers to represent complex graphs, spheres, and other shapes. Not only were you able to represent those elements, but you could also use numeric matrices and vectors to expand them, shrink them, rotate them, and do all manner of linear transformations.

Our hypothesis in the case of generative AI is that we can potentially adequately and sensibly represent the features within generative AI by a linear form of representation. This could be characterized as the linear representation hypothesis.

Why is it a hypothesis?

Because we might end up realizing that a linear representation won’t cut the mustard. Maybe it is insufficient for the task at hand. Perhaps we need to find some other form of representation to suitably codify and make use of features within generative AI. Right now, it seems like the right means, but we must scientifically and systematically ask ourselves whether it is fully worthy or if we need to switch to alternative means.

The superposition hypothesis is a related cousin.

I will playfully engage you in figuring out what the superposition hypothesis consists of in the context of generative AI. If you know something about physics and the role of superposition in that realm, you admittedly have a leg up on this.

Suppose you decided to watch one artificial neuron in a vast artificial neural network that sits at the core of a generative AI app. All day long, you sit there, patiently waiting for that one artificial neuron to be kicked into action. A numeric value finally flows into the artificial neuron. It does the needed calculations and then outputs a value that then flows along to another artificial neuron.

Eureka, you yell out. The artificial neuron that you had so tenderly observed was finally activated and did so when the word “dog” had been entered as part of a prompt.

Can you conclude that this one artificial neuron is solely dedicated to the facets of “dog”?

Maybe, or maybe not.

We might feed in a prompt that has the word “cat” and see this same artificial neuron be activated. There could be lots of other situations that activate this one artificial neuron. Making a brash assumption that this artificial neuron has only one singular purpose is a gutsy move. You might be right, or you might be wrong.

The world would be easier if each artificial neuron had only one purpose. Think of it this way. Once you ferreted out the purpose, you are done and never need to revisit that artificial neuron. You know what it does. Case closed.

In physics, a similar question has arisen, for example about waves. A given wave might encode multiple waves and therefore in a sense have multiple uses. A regular dictionary defines superposition as the act of having two or more things that coincide with each other.

Our use here is that it seems reasonable to believe that artificial neurons will have more than just one singular purpose. They will encode facets that will apply to more than one feature. When examining and discerning what an artificial neuron represents, we need to keep an open mind and expect that there will be multiple uses involved.

But that’s just a hypothesis, namely the superposition hypothesis.

I’m sure you know that in 1969, Astronaut Neil Armstrong stepped onto the lunar surface and uttered the immortal words “That’s one small step for man, one giant leap for mankind.”

When it comes to generative AI, the rush toward widely adopting generative AI and large language models is vast and growing in leaps and bounds. Generative AI is going to be ubiquitous. If that’s the case, we certainly ought to know what is happening inside the inner sanctum of generative AI.

A lot of small steps are still ahead of us.

Let’s aim to make a giant leap for all of humankind.

• Editorial Standards
• Reprints & Permissions

Join The Conversation

One Community. Many Voices. Create a free account to share your thoughts. 

Forbes Community Guidelines

Our community is about connecting people through open and thoughtful conversations. We want our readers to share their views and exchange ideas and facts in a safe space.

In order to do so, please follow the posting rules in our site's  Terms of Service.   We've summarized some of those key rules below. Simply put, keep it civil.

Your post will be rejected if we notice that it seems to contain:

• False or intentionally out-of-context or misleading information
• Insults, profanity, incoherent, obscene or inflammatory language or threats of any kind
• Attacks on the identity of other commenters or the article's author
• Content that otherwise violates our site's  terms.

User accounts will be blocked if we notice or believe that users are engaged in:

• Continuous attempts to re-post comments that have been previously moderated/rejected
• Racist, sexist, homophobic or other discriminatory comments
• Attempts or tactics that put the site security at risk
• Actions that otherwise violate our site's  terms.

So, how can you be a power user?

• Stay on topic and share your insights
• Feel free to be clear and thoughtful to get your point across
• ‘Like’ or ‘Dislike’ to show your point of view.
• Protect your community.
• Use the report tool to alert us when someone breaks the rules.

Thanks for reading our community guidelines. Please read the full list of posting rules found in our site's  Terms of Service.

10 Ways to Detect AI Writing Without Technology

As more of my students have submitted AI-generated work, I’ve gotten better at recognizing it.

AI-generated papers have become regular but unwelcome guests in the undergraduate college courses I teach. I first noticed an AI paper submitted last summer, and in the months since I’ve come to expect to see several per assignment, at least in 100-level classes.

I’m far from the only teacher dealing with this. Turnitin recently announced that in the year since it debuted its AI detection tool, about 3 percent of papers it reviewed were at least 80 percent AI-generated.

Just as AI has improved and grown more sophisticated over the past 9 months, so have teachers. AI often has a distinct writing style with several tells that have become more and more apparent to me the more frequently I encounter any.

Before we get to these strategies, however, it’s important to remember that suspected AI use isn’t immediate grounds for disciplinary action. These cases should be used as conversation starters with students and even – forgive the cliché – as a teachable moment to explain the problems with using AI-generated work. 

To that end, I’ve written previously about how I handled these suspected AI cases , the troubling limitations and discriminatory tendencies of existing AI detectors , and about what happens when educators incorrectly accuse students of using AI . 

With those caveats firmly in place, here are the signs I look for to detect AI use from my students. 

1. How to Detect AI Writing: The Submission is Too Long 

When an assignment asks students for one paragraph and a student turns in more than a page, my spidey sense goes off. 

Tech & Learning Newsletter

Tools and ideas to transform education. Sign up below.

Almost every class does have one overachieving student who will do this without AI, but that student usually sends 14 emails the first week and submits every assignment early, and most importantly, while too long, their assignment is often truly well written. A student who suddenly overproduces raises a red flag.

2. The Answer Misses The Mark While Also Being Too Long

Being long in and of itself isn’t enough to identify AI use, but it's often overlong assignments that have additional strange features that can make it suspicious. 

For instance, the assignment might be four times the required length yet doesn’t include the required citations or cover page. Or it goes on and on about something related to the topic but doesn’t quite get at the specifics of the actual question asked. 

3. AI Writing is Emotionless Even When Describing Emotions 

If ChatGPT was a musician it would be Kenny G or Muzak. As it stands now, AI writing is the equivalent of verbal smooth jazz or grey noise. ChatGPT, for instance, has this very peppy positive vibe that somehow doesn’t convey actual emotion. 

One assignment I have asks students to reflect on important memories or favorite hobbies. You immediately sense the hollowness of ChatGPT's response to this kind of prompt. For example, I just told ChatGPT I loved skateboarding as a kid and asked it for an essay describing that. Here’s how ChatGPT started: 

As a kid, there was nothing more exhilarating than the feeling of cruising on my skateboard. The rhythmic sound of wheels against pavement, the wind rushing through my hair, and the freedom to explore the world on four wheels – skateboarding was not just a hobby; it was a source of unbridled joy.

You get the point. It’s like an extended elevator jazz sax solo but with words.  

4. Cliché Overuse

Part of the reason AI writing is so emotionless is that its cliché use is, well, on steroids.

Take the skateboarding example in the previous entry. Even in the short sample, we see lines such as “the wind rushing through my hair, and the freedom to explore the world on four wheels.” Students, regardless of their writing abilities, always have more original thoughts and ways of seeing the world than that. If a student actually wrote something like that, we’d encourage them to be more authentic and truly descriptive.

Of course, with more prompt adjustments, ChatGPT and other AI’s tools can do better, but the students using AI for assignments rarely put in this extra time.

5. The Assignment Is Submitted Early

I don’t want to cast aspersions on those true overachievers who get their suitcases packed a week before vacation starts, finish winter holiday shopping in July, and have already started saving for retirement, but an early submission may be the first signal that I’m about to read some robot writing.

For example, several students this semester submitted an assignment the moment it became available. That is unusual, and in all of these cases, their writing also exhibited other stylistic points consistent with AI writing.

Warning: Use this tip with caution as it is also true that many of my best students have submitted assignments early over the years.

6. The Setting Is Out of Time

AI image generators frequently have little tells that signal the AI model that created it doesn’t understand what the world actually looks like — think extra fingers on human hands or buildings that don’t really follow the laws of physics.

When AI is asked to write fiction or describe something from a student’s life, similar mistakes often occur. Recently, a short story assignment in one of my classes resulted in several stories that took place in a nebulous time frame that jumped between modern times and the past with no clear purpose.

If done intentionally this could actually be pretty cool and give the stories a kind of magical realism vibe, but in these instances, it was just wonky and out-of-left-field, and felt kind of alien and strange. Or, you know, like a robot had written it.

7. Excessive Use of Lists and Bullet Points  

Here are some reasons that I suspect students are using AI if their papers have many lists or bullet points: 

1. ChatGPT and other AI generators frequently present information in list form even though human authors generally know that’s not an effective way to write an essay. 

2. Most human writers will not inherently write this way, especially new writers who often struggle with organizing information.

3. While lists can be a good way to organize information, presenting more complex ideas in this manner can be .…

4 … annoying. 

5. Do you see what I mean? 

6. (Yes, I know, it's ironic that I'm complaining about this here given that this story is also a list.)

8. It’s Mistake-Free 

I’ve criticized ChatGPT’s writing here yet in fairness it does produce very clean prose that is, on average, more error-free than what is submitted by many of my students. Even experienced writers miss commas, have long and awkward sentences, and make little mistakes – which is why we have editors. ChatGPT’s writing isn’t too “perfect” but it’s too clean.  

9. The Writing Doesn’t Match The Student’s Other Work  

Writing instructors know this inherently and have long been on the lookout for changes in voice that could be an indicator that a student is plagiarizing work. 

AI writing doesn't really change that. When a student submits new work that is wildly different from previous work, or when their discussion board comments are riddled with errors not found in their formal assignments, it's time to take a closer look. 

10. Something Is Just . . . Off 

The boundaries between these different AI writing tells blur together and sometimes it's a combination of a few things that gets me to suspect a piece of writing. Other times it’s harder to tell what is off about the writing, and I just get the sense that a human didn’t do the work in front of me. 

I’ve learned to trust these gut instincts to a point. When confronted with these more subtle cases, I will often ask a fellow instructor or my department chair to take a quick look (I eliminate identifying student information when necessary). Getting a second opinion helps ensure I’ve not gone down a paranoid “my students are all robots and nothing I read is real” rabbit hole. Once a colleague agrees something is likely up, I’m comfortable going forward with my AI hypothesis based on suspicion alone, in part, because as mentioned previously, I use suspected cases of AI as conversation starters rather than to make accusations. 

Again, it is difficult to prove students are using AI and accusing them of doing so is problematic. Even ChatGPT knows that. When I asked it why it is bad to accuse students of using AI to write papers, the chatbot answered: “Accusing students of using AI without proper evidence or understanding can be problematic for several reasons.” 

Then it launched into a list. 

• Best Free AI Detection Sites
• My Student Was Submitting AI Papers. Here's What I Did
• She Wrote A Book About AI in Education. Here’s How AI Helped

Erik Ofgang is a Tech & Learning contributor. A journalist,  author  and educator, his work has appeared in The New York Times, the Washington Post, the Smithsonian, The Atlantic, and Associated Press. He currently teaches at Western Connecticut State University’s MFA program. While a staff writer at Connecticut Magazine he won a Society of Professional Journalism Award for his education reporting. He is interested in how humans learn and how technology can make that more effective. 

Best Apps and Sites for Augmented Reality

What Is Scratch And How Does It Work? What's New?

What Is Blooket And How Does It Work? Tips & Tricks

Most Popular