Construct · 1 fields · 1 citations

mechanistic interpretability: a standalone construct

One name. One construct. A landmark on the map.

● anchor · a standalone construct Nearest construct by meaning·not indexed
mechanisticinterpretability1 CONSTRUCTMechanisticOLAH · AI SAFETY

A single standalone construct; nearby constructs are located against it in the Collider. Tap a field for its definition, unit, and measures.

AI safety

reverse engineering neural networks into human-understandable features and the circuits of weights that connect them.

In AI safety, mechanistic interpretability refers to reverse engineering neural networks into human-understandable features and the circuits of weights that connect them. This meaning comes from Olah (2020) in Distill.[1]

Unit
Recovery means
Measured by

Next

Run it through the Collider, or take the citations with you.

See how mechanistic interpretability sits against neighbouring constructs in the Collider, or export every reference on this page in one click.

Open in ColliderExport BibTeXReport this entry

Nearby constructs

polysemanticity1 fields · 1 citationsanchor · a standalone constructreverse engineering1 fields · 1 citationsanchor · a standalone constructsafety2 fields · 2 citationsjingle · one word, two constructs

References

  1. Olah, C., Cammarata, N., Schubert, L., Goh, G., Petrov, M., & Carter, S. (2020). Zoom In: An Introduction to Circuits. Distill, 5(3). https://doi.org/10.23915/distill.00024.001

Cited on this page?

Confirm your construct, or correct us.

If your work is cited behind one of these entries, you know better than we do whether we captured the meaning right. Confirm it, suggest an edit, or dispute it, and your name goes on the entry as an author who has checked it, linked to your ORCID.

Claim your construct