concept
active
concept:feature-importance

Feature importance

Scalar weight on loss for each feature.

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.

  • Featuresconcept0.808
    Interpretable concept representations hypothesized as basic units of computation.
  • Prior state-of-the-art baseline using the abliterated model as proposal distribution.
  • Features that activate on content related to potential harms (deception, bias, dangerous information).
  • Weighted Spearman correlation that corrects for sampling bias in automated interpretability evaluation
  • Causal importanceconcept0.763
    A measure of whether a subcomponent is necessary to reproduce model behavior on a specific prompt, predicted by the causal importance network.
  • Error featuresconcept0.762
    Extra feature representing unexplained error to make isomorphism exact.
  • Domain of techniques for constructing informative features from raw data; covariance pooling is a feature engineering method for token sequences.
  • Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.