finding
active
finding:r1-general-reasoning-sae-learned-features-reconstructing-reasoning-behaviors-such-as-backtracking

R1 general reasoning SAE learned features reconstructing reasoning behaviors such as backtracking

Curated features show core reasoning behaviors are captured.

Source paper

extracted_from
Under the Hood of a Reasoning Model - Goodfire
Dron Hazra

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Reasoning behavior for which the SAEs learned features.

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.