Skip to content

Attention Mechanisms: First Intuition

Why this matters

The full attention lesson uses words like vectors, scores, weights, query, key, value, masking, and heads.

This page gives you the basic idea first, without math or code.

Attention is the reason a transformer can look at a word and ask:

Which other words help me understand this word?

If that sentence makes sense, the detailed lesson becomes much easier to read.

Mental model

Attention is controlled looking.

Imagine this sentence:

The cat sat on the mat because it was tired.

The word it is unclear by itself.

To understand it, you look back at the sentence:

it probably refers to cat

That is the basic intuition behind attention. A model updates its understanding of one word by looking at other words and deciding which ones matter most.

Core ideas

  • A word by itself is often not enough.
  • Attention lets each token look at other tokens.
  • The model does not simply copy one word; it mixes information from several words.
  • Attention weights are like percentages of focus.
  • A context vector is the updated meaning after borrowing context.
  • Query, key, and value are three roles used to decide what to look at and what to borrow.
  • Causal masking means “no peeking at future words.”
  • Multi-head attention means several attention teams look for different patterns at the same time.

Walkthrough

Start with an unclear word

Take this sentence:

The cat sat on the mat because it was tired.

Focus on the word:

it

The word it needs help. It could refer to different things, but in this sentence the most likely meaning is:

it = the cat

A human resolves this almost automatically. A transformer needs a mechanism for doing something similar with numbers.

That mechanism is attention.

Attention means looking around

For the word it, the model might look at the sentence like this:

Word How useful for understanding it?
The not very useful
cat very useful
sat somewhat useful
on not very useful
the not very useful
mat a little useful
because useful for relationship
it current word
was useful for grammar
tired useful for meaning

The model is not thinking in English like this, but this table captures the idea.

Some words matter more than others.

Attention weights are like percentages

The model turns “how useful is this word?” into attention weights.

A simplified version might look like:

cat      55%
tired    20%
sat      10%
because   8%
mat       4%
other     3%

These percentages are not manually written by a human. The model learns how to produce them during training.

The important idea:

larger weight = borrow more information from that word
smaller weight = borrow less information from that word

Attention is borrowing, not just pointing

Attention does not only choose one word.

It mixes information.

For it, the model may mostly borrow from cat, but also borrow some information from tired, sat, and because.

Plain version:

old understanding:
it

after attention:
it, probably meaning the cat, connected to being tired

The full lesson calls this updated representation a context vector.

You can read “context vector” as:

the word's updated meaning after looking around

Score, normalize, mix

The full lesson says attention has three recurring steps:

score -> normalize -> mix

In plain language:

compare -> turn into percentages -> borrow information

Mapping:

Full lesson term Plain meaning
attention score rough match strength
attention weight percentage of focus
context vector updated word representation

If you remember only one thing from this page, remember:

Attention compares words, turns the comparisons into weights, then mixes information using those weights.

Query, key, and value

The full lesson introduces query, key, and value.

These sound abstract, but the roles are simple.

Imagine every word carries three cards:

query = what I am looking for
key   = what I can be matched by
value = what useful information I can give

For the word it:

query:
I am looking for the thing I refer to.

For the word cat:

key:
I am a possible thing being discussed.

value:
I contribute information about the cat.

So attention works like:

query from it matches key from cat
therefore borrow value from cat

This is why the detailed lesson says:

queries and keys decide the weights
values provide the information that gets mixed

Why not just use the original words?

Because the same word can mean different things in different sentences.

Example:

The bank approved the loan.
The bank flooded after the storm.

The word bank needs context.

In the first sentence, it means a financial institution.

In the second sentence, it may mean land beside water.

Attention helps the model adjust a token's representation based on nearby and relevant tokens.

Causal masking means no peeking ahead

GPT-style models generate text from left to right.

When predicting the next word, the model should not see the future answer.

Example:

The cat sat on the ___

If the target answer is:

mat

the model should not be allowed to look at mat while learning to predict it.

Causal masking is the rule:

you may look left
you may look at yourself
you may not look right

Plain table:

Current token Allowed to look at
The The
cat The, cat
sat The, cat, sat
on The, cat, sat, on

The full lesson calls this a causal mask.

Read it as:

no peeking at future words

Multi-head attention means several attention teams

One attention mechanism can look for one kind of relationship.

But language has many relationships at once:

  • which word does it refer to?
  • which words form a phrase?
  • which subject matches which verb?
  • which earlier words set the topic?

Multi-head attention means the model runs several attention mechanisms in parallel.

Plain version:

head 1 looks for pronoun references
head 2 looks for nearby phrase structure
head 3 looks for topic words
head 4 looks for grammar patterns

The heads are not manually assigned these jobs. They learn different patterns during training.

The important idea:

multi-head attention = several attention teams looking at the same sentence in different ways

Term Decoder

Use this table when reading the full lesson.

Full lesson term Read it as
token a piece of text, often a word or part of a word
token embedding the model's numeric representation of a token
attention score how strongly two tokens match before cleanup
softmax the cleanup step that turns scores into percentages
attention weight the percentage of focus assigned to a token
value vector the information borrowed from a token
context vector the updated token representation after borrowing
query what the current token is looking for
key what another token offers for matching
causal mask the no-peeking-at-future-words rule
attention head one attention team

Common traps

Do not think attention is human understanding

Attention is a learned way to mix information between token representations. It can support useful behavior, but it is not the same as human comprehension.

Do not think attention picks only one word

Attention usually mixes information from many tokens, with some receiving larger weights than others.

Do not worry about the math first

The detailed lesson explains dot products, softmax, and tensor shapes. For now, understand the story: compare, turn into percentages, borrow.

Do not treat query, key, and value as separate words

They are three learned views of the same token representation, used for matching and information mixing.

Do not skip masking in GPT-style models

Without causal masking, a model could look ahead at future tokens during training, which breaks left-to-right generation.

Check yourself

Why does the word it need attention in the cat example?

Because it is unclear alone. Attention lets the model look at other words, especially cat, to build a better representation.

What are attention weights like in plain language?

They are like percentages of focus: how much information to borrow from each token.

What is a context vector?

It is the updated representation of a token after it has borrowed information from other tokens.

What do query, key, and value mean?

Query means what I am looking for, key means what I can be matched by, and value means what information I can contribute.

What does causal masking prevent?

It prevents tokens from looking at future tokens.

What is multi-head attention?

Several attention mechanisms running in parallel so the model can look for different patterns at the same time.

Now Read the Full Lesson

Next, read Attention Mechanisms: Why the Math Looks Like This.

That bridge explains dot products, same direction, softmax, weights that sum to 1, and scaling before you move into the full implementation lesson.

After that, read Attention Mechanisms.

When you get there, translate the technical terms like this:

score, normalize, mix -> compare, turn into percentages, borrow
query/key/value       -> looking for / match label / useful content
causal mask           -> no peeking ahead
multi-head attention  -> several attention teams

The full lesson adds the math and PyTorch version of the same idea.

Source anchors

  • Supports: study-guide/docs/lessons/13-attention-mechanisms.md
  • Source file: notebooks/Module2/13-Attention Mechanisms.ipynb