concept
active
concept:atomic-features

atomic features

The idea that interpretability should decompose representations into minimal, indivisible feature units; contrasted with manifold-level descriptions.

Neighborhood — ranked by edge-count

Papers (1)

paper

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.

  • Featuresconcept0.804
    Interpretable concept representations hypothesized as basic units of computation.
  • Fourier featuresconcept0.743
    Features identified in Llama-3.1-8B that compute sums using periods respecting base-10 addition (2, 5, 10) rather than concept-specific periods
  • Action Featuresconcept0.740
    Dual interpretation of features: in addition to responding to inputs, features also act to increase probability of specific output tokens
  • Attentional featuresframework0.738
    Proposed attention analog of sparse monosemantic features for decomposing attention layers.
  • Shared featuresconcept0.730
    Features with similar decoder magnitude across both models.
  • Functionally significant directions in the residual stream that organize activations in mechanistic interpretability
  • Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
  • Echo featuresconcept0.721
    Repeated features activating on similar inputs, expected under L1 penalty.