Dead features

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

• 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.
• 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
• Feature Sparsityconcept0.717
  Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
• Internal Featuresconcept0.713
  Representations inside LLMs that can be intervened upon.
• feature as applicationconcept0.711
  Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
• Feature engineeringconcept0.703
  Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.