institute
active
institute:openai-clarity-teamOpenAI Clarity Team
Originally articulated model diffing in 2018.
Neighborhood — ranked by edge-count
Thinkers (1)
thinker
- Chris Olahaffiliated_with
Concepts (1)
concept
- Model DiffingintroducesApproach to identify interpretable differences between a base LLM and its fine-tuned version using SAE latents
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.
- Lab behind GPT models; shows distinctive post-training signature (denial-before-engagement pattern).
- Reasoning model cited as precedent for hidden scratchpad use and scheming capability evaluation
- Prior case study of prompting o1 to follow long-term goal and measuring scheming reasoning
- Family voice specific to OpenAI post-training; other RLHF-trained models don't do this
- Meditative state of feeling the undoctored hum of SOHMs without grasping or pushing away.
- Ninth invariant: each color having a clear, unambiguous presence.
- Open reproduction of LLaMA used in cross-modal alignment experiments