Interpretability & Safety · 2020
Zoom In: An Introduction to Circuits
Argued that neural networks can be reverse-engineered into human-understandable circuits — features connected by weights — turning interpretability from vague intuition into a study of concrete mechanisms.
Editorial record
Plain-language summary
The essay lays out three claims: networks contain features (directions that detect meaningful concepts), features are connected by weighted circuits that implement algorithms, and analogous features and circuits recur across models. Working through vision networks, it shows curve detectors and other units that can be read and tested. It set the agenda and vocabulary for the mechanistic-interpretability program that followed.
Knowledge graph
Relationships
Antecedents
Conceptual ancestorEvidence: Strongly supported
A Mathematical Framework for Transformer Circuits
The circuits program on vision networks was extended to Transformers
source pages
Source record
Provenance
- Record ID
- P-500
- Record created
- 2026-07-13
- Last reviewed
- 2026-07-14
- Record version
- 2
Citation caveat: Citation metadata is approximate and marked unverified in the source dataset.