concept
active
concept:dead-features

Dead features

SAE features that never activate on a large sample of data, indicating inefficient dictionary use.

Neighborhood — ranked by edge-count

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.

  • Featuresconcept0.753
    Interpretable concept representations hypothesized as basic units of computation.
  • Action Featuresconcept0.752
    Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
  • C_deadconcept0.750
    The class of dead buildings, essentially all configurations except the living ones; almost coextensive with C_all.
  • Error featuresconcept0.746
    Extra feature representing unexplained error to make isomorphism exact.
  • Feature Densityconcept0.733
    Fraction of training tokens on which a given feature has nonzero activation; used as proxy metric for autoencoder quality
  • Pure Featureconcept0.726
    A feature that responds to only a single latent variable, contrasted with polysemantic features
  • Premise that models represent concepts as features.
  • Feature Sparsityconcept0.717
    Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work