institute
active
institute:anthropic-interpretability-teamAnthropic interpretability team
The team that produced this developing-work update.
Neighborhood — ranked by edge-count
Thinkers (8)
thinker
- Jack Lindseyaffiliated_with
- Trenton Brickenaffiliated_with
- Christopher Olahaffiliated_with
- Adam Jermynaffiliated_with
- Jonathan Marcusaffiliated_with
- Kelley Rivoireaffiliated_with
- Thomas Henighanaffiliated_with
- Siddharth Mishra-Sharmaaffiliated_with
Papers (1)
paper
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Authors' affiliation.
- Lab behind Claude models and Constitutional AI training approach; represents highest baseline scores and lowest prompt lift.
- Antra's explanation for why even stronger evidence may exist but remains unpublished.
- Cited as activation-level support for the performing care vs having care distinction the battery detects behaviorally
- Method using large language models (Claude) to generate and test explanations of features at scale
- The capability to explain model predictions; a central theme of the paper, with disruption profiles as vehicle.
- Frames model interpretability like biology, features as cells, tools as microscopes.
- Proposed paradigm for evaluating interpretability work through empirical falsifiability rather than benchmarks or user studies