concept
active
concept:action-features

Action Features

Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Feature that fires on a specific token only within a specific surrounding context (e.g., 'the' in physics vs 'the' in mathematics)

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.

  • actionconcept0.839
    Changing configuration to sample environment differently; minimizes free energy.
  • Featuresconcept0.812
    Interpretable concept representations hypothesized as basic units of computation.
  • Action Selectionconcept0.809
    Choice of policies minimizing expected free energy to realize preferred future states.
  • Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
  • Synthesizing inputs maximizing component activation.
  • Attentional featuresframework0.768
    Proposed attention analog of sparse monosemantic features for decomposing attention layers.
  • Internal concepts a model uses, extracted as human-interpretable components.
  • Error featuresconcept0.766
    Extra feature representing unexplained error to make isomorphism exact.