# Attention relationship

Concept · [Building with AI](https://ecosystem.samcarlton.com/ai)

Also called: token relationship, attention pair, attention weights, attention score, attention scores

The link between two [tokens in](https://ecosystem.samcarlton.com/input-tokens) the input, measured by how much one shapes the model's reading of the other. Every [token](https://ecosystem.samcarlton.com/token) can relate to every other one, so these links multiply fast: double the text and you get roughly four times as many.

**For example:** In a long contract, a clause on page 9 that mentions 'the fee above' has an attention relationship with the fee set out on page 2.

## Connects to (5)

- [Attention](https://ecosystem.samcarlton.com/attention): The part of a language model that decides, for each token, how much every other token in the input should shape its meaning.
- [Token](https://ecosystem.samcarlton.com/token): In AI, a small chunk of text, roughly a word or a piece of a word, that an LLM reads and writes.
- [Attention budget](https://ecosystem.samcarlton.com/attention-budget): A way of picturing attention as a fixed amount each token can spread across everything else in the input.
- [Attention degradation](https://ecosystem.samcarlton.com/attention-degradation): The drop in an agent's sharpness as a session gets long.
- [Context window](https://ecosystem.samcarlton.com/context-window): How much text an LLM can take into account at one time.

Map view: https://ecosystem.samcarlton.com/attention-relationship