INTERP ATLAS

phenomenon

safety-relevant-features

1 entry

2024 (1)

IA-003

Scaling Monosemanticity is showing , about and .

Adly Templeton; Tom Conerly; Jonathan Marcus; Jack Lindsey; Trenton Bricken; Brian Chen; Adam Jermyn; et al. · Anthropic

First demonstration that sparse autoencoders scale from toy models to a frontier production model, published as a browsable index of millions of features — including the Golden Gate Bridge feature that later became a public demo.

The moment interpretability stopped being a toy-model science, and the origin of the field's most famous public artefact.

HighRead the article; cross-referenced in BlueDot and ACX pieces, 2026-08-06

open full entry