Easy Attention Question 16 of 223

What is self-attention?

GenAI / LLM · Speak this in 60–90 seconds · Faridabad & Delhi NCR

The model does not read letters like humans. It reads these pieces, then predicts the next one.

Self-attention computes attention among tokens of the same sequence.

LLMs use tokens (not full words) because it helps them:

Attention questions separate people

who only read docs from people who shipped.

Keep it short, concrete,

and tied to GenAI / LLM work.

Stable token IDs

Each piece maps to a number the network can learn.

Fits the model

Fixed pieces are what transformers expect as input.

Before the model can read a sentence, it goes through these steps:

1
Self-attention computes attention among
tokens of the same sequence.
2
Each token builds a
new representation from a weighted mix of the others.
3
That is how a
word like 'bank' picks up river versus finance from nearby context.
4
Context mix
Attention looks at nearby tokens together.
5
Next token
The model scores what should come next.
6
Decode
IDs turn back into readable text.

Let's see how a real sentence is tokenized (tokens may vary by model):

Input text

“Each token builds a new representation from a weighted mix of the others.”

Tokenized output

Eachtokenbuildsanewrepresentation

Token IDs (example)

2987408337471632900

Note: Actual tokens and IDs depend on the tokenizer (e.g., GPT, Llama, etc.).

Self-attention computes attention among tokens of the same sequence. Each token builds a new representation from a weighted mix of the others.