← People

Tom Conerly

Source-listed: Core Research Contributor · Anthropic

Record snapshot: Sep 3, 2026. Coverage and affiliations may be incomplete or historical.

Selected work

5
  1. Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 SonnetSaved credit: Contributor · 2024Explore people connected to this work →
  2. Constitutional AI: Harmlessness from AI FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
  3. Training a Helpful and Harmless Assistant with Reinforcement Learning from Human FeedbackSaved credit: Contributor · 2022Explore people connected to this work →
  4. Language Models (Mostly) Know What They KnowSaved credit: Contributor · 2022Explore people connected to this work →
  5. Predictability and Surprise in Large Generative ModelsSaved credit: Contributor · 2022Explore people connected to this work →