concept
active
concept:features

Features

Interpretable concept representations hypothesized as basic units of computation.

Neighborhood — ranked by edge-count

Frameworks (1)

framework

Hypotheses (1)

hypothesis

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.

  • Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
  • Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
  • Error featuresconcept0.829
    Extra feature representing unexplained error to make isomorphism exact.
  • Feature utilityconcept0.824
    Frequency-weighted spectral value πkλkj determining which features are retained.
  • Internal concepts a model uses, extracted as human-interpretable components.
  • Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
  • Synthesizing inputs maximizing component activation.
  • Attentional featuresframework0.815
    Proposed attention analog of sparse monosemantic features for decomposing attention layers.