concept
active
concept:features-sae-features

Features (SAE features)

Internal concepts a model uses, extracted as human-interpretable components.

Neighborhood — ranked by edge-count

Concepts (2)

concept
  • The individual, supposedly monosemantic directions learned by SAEs; argued here to fragment manifolds into disconnected pieces.
  • Echo features
    associated_with
    Repeated features activating on similar inputs, expected under L1 penalty.

Artifacts (1)

artifact
  • Desktop chat interface for feature understanding and steering; deprecated Feb 2026.

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.