concept
active
concept:shared-features

Shared features

Features with similar decoder magnitude across both models.

Neighborhood — ranked by edge-count

Concepts (1)

concept

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.

  • Featuresconcept0.802
    Interpretable concept representations hypothesized as basic units of computation.
  • Property of features that form consistently across different models trained on the same or similar data, suggesting features are real representational units
  • Patterns of which features activate together across tokens; preserved by covariance pooling but lost in mean pooling.
  • Feature splittingconcept0.794
    Phenomenon where a feature in a small SAE splits into multiple finer features in a larger SAE.
  • Uninstantiated variables used for communication in concurrent logic programming.
  • Baseline from Mishra-Sharma et al. dedicating features to shared variance.
  • Proposed variation designating ~10k of ~250k features as shared with penalty 0.1-0.2x baseline to soak up shared variance.
  • Problems suggesting sparsity breaks down as interpretability proxy.