concept
active
concept:reasoning-modelReasoning model
Models like R1 that produce chain-of-thought and backtrack; claimed qualitatively different from non-reasoning LMs.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Reasoning Modelssame_asClass of large language models designed to produce extended chain-of-thought before answering, studied in this paper
Artifacts (1)
artifact
- Two open-sourced SAEs, the first public interpreters for a true reasoning model at this scale.
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.
- A representation that captures relevant aspects of a system; according to the theorem, the regulator must embody this.
- Probability of data under the model, penalizing complexity and rewarding accuracy.
- Primary test domain for manifold steering, including reasoning and ICL tasks
- Norman's design model vs user model; a mental conception of how a system works.
- Future direction.
- Agent's internal probabilistic model of environment; enables belief inference about hidden states given outcomes.
- Primary substrate for manifold steering experiments; demonstrates method on reasoning and in-context tasks.
- Success in cognitive science motivates the approach.