A field guide to AI positions

Attention & self-attention

Inside a model.

Source is over 18 months old.

Publication dates and source age

Sources counted: 1

Newest dated source: 2017-06-12

Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

Open in the glossary Reading notes · Structured record

Prepared with AI assistance. Not independently fact-checked. Original sources and qualifications are below.

In plain language

A calculation that mixes information from different input positions with different weights. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-attention-1a5192ba3d7825ca26b24a72. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Limits & distinctions

Attention is one operation within a larger network. The name does not imply a separate reader or human-like concentration. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-attention-09422ce4d5c74cb753a9bb98. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

A fuller explanation

The weights depend on the input. In self-attention, parts of one sequence supply the information being combined. Multiple attention heads perform different learned combinations in parallel. [1]

Reference this explanation or suggest a correction

Explanation based on the linked sources. Claim ID: claim-term-attention-1e4c26398ee834b2e16dc7b8. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

How it relates to the map

Use it to read Transformer diagrams. It describes a component, not an actor’s position. [1]

Reference this explanation or suggest a correction

Editorial interpretation or qualification. Claim ID: claim-term-attention-25f52a21ad9f2e54a62ed1b2. Edition 0.20.0.

Link to this explanation · Suggest a correction · How corrections work

Share this page

https://theaiatlas.org/ideas/attention/

Download a share image · Vector image

Image previews are summaries. Keep the page link so readers can check the evidence.

Sources and what we read

  1. 1. Attention Is All You Need

    Ashish Vaswani and coauthors / arXiv · First-hand source · Published 2017-06-12 · Updated 2023-08-02 · Material last read 2026-09-15

    Source is over 18 months old.

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2017-06-12

    Assessed at this edition's evidence cutoff: 2026-09-15. 18-month boundary: 2025-03-15.

    Publication age does not tell us whether a claim is still valid. Reading an old source again does not make its publication date newer. An update date does not establish that the passage we used was updated.

    Read scope is described in the source note.

    No archive check recorded.

    Read abstract, model architecture, learned embeddings and next-token probabilities in the HTML paper; publication and revision dates checked against the arXiv abstract page. This is the original Transformer architecture, not a claim that every current LLM has its exact structure.

    Source ID: transformer-paper

Edition and machine-readable evidence

Content version 0.20.0. Evidence cutoff 2026-09-15; this does not mean every source was read on that day.

Pinned complete dataset · Complete evidence page · Agent consumption guide