A field guide to AI positions

Parameters & weights

Publication dates and source age

Sources counted: 4

Newest dated source: 2025-03-27

At least one source was published within the 18-month window.

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

Some publication dates are unknown; the newest dated source may not be the newest source overall.

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

In plain language

The numerical settings learned during training that shape how a model processes input. [1] [2]

Reference this explanation or suggest a correction

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

Limits & distinctions

Listing all the numbers does not give a readable explanation of every answer. Interpretability research tries to connect internal calculations to behavior. [4]

Reference this explanation or suggest a correction

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

A fuller explanation

In a neural network, weights control how strongly values contribute to later calculations. Biases are another kind of parameter: added numerical offsets. Together, parameters help determine the output the network produces. [1]

Reference this explanation or suggest a correction

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

How it relates to the map

Useful when a model description gives a parameter count or discusses changing weights. [3]

Reference this explanation or suggest a correction

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

Share this page

https://theaiatlas.org/ideas/parameters/

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. Neural networks: Nodes and hidden layers

    Publication dates and source age

    Sources counted: 1

    Publication dates are unavailable.

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

    Some publication dates are unknown; the newest dated source may not be the newest source overall.

    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 the explanations of connected layers, numerical weights and biases, and calculations. Did not run the embedded exercises. Used for the mathematical structure, not a claim that an artificial network reproduces a human brain.

  2. 2. Linear regression: Gradient descent

    Publication dates and source age

    Sources counted: 1

    Publication dates are unavailable.

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

    Some publication dates are unknown; the newest dated source may not be the newest source overall.

    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 the iterative prediction, loss and parameter-update explanation. The page's guarantees for convex linear regression are not extended here to neural-network training. Updated date follows the page; initial publication is unspecified.

  3. 3. Models

    Publication dates and source age

    Sources counted: 1

    Publication dates are unavailable.

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

    Some publication dates are unknown; the newest dated source may not be the newest source overall.

    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 architecture, weights, checkpoints, loading and saving. Used to distinguish a model's structure and learned values from the application around it. Example code was read, not executed; live page publication date unspecified.

  4. 4. Circuit Tracing: Revealing Computational Graphs in Language Models

    Publication dates and source age

    Sources counted: 1

    Newest dated source: 2025-03-27

    At least one source was published within the 18-month window.

    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 introduction, method overview and limitations including reconstruction errors, graph complexity, global circuits and mechanistic faithfulness. The authors' replacement-model analyses reveal selected mechanisms; they do not provide a complete explanation of all behavior. Later attention-tracing work is cited alongside this paper to avoid treating its missing-attention limitation as a permanent field-wide result.

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