concept
active
concept:error-features

Error features

Extra feature representing unexplained error to make isomorphism exact.

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Idea that decomposed components must causally reflect the model's computation; enforced by adversarial ablation in VPD.

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.

  • Featuresconcept0.829
    Interpretable concept representations hypothesized as basic units of computation.
  • Feature utilityconcept0.797
    Frequency-weighted spectral value πkλkj determining which features are retained.
  • 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.
  • Prediction Errorconcept0.780
    Role in optimizing sensory states; unified treatment shows value-learning and perception share error-minimization principle.
  • When non-orthogonal features cause logistic regression to identify a suboptimal probe direction
  • Cost of non-orthogonal feature embedding.
  • Internal concepts a model uses, extracted as human-interpretable components.