Feature co-occurrence

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.

• Feature Sparsityconcept0.768
  Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
• Properties in each cluster appear to be similar or interrelatedclaim0.755
  Interpretive claim that the statistically derived clusters reflect conceptual similarity or interdependence among the properties.
• Superposition of Sparse Featuresconcept0.754
  Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption
• Close Association Featureconcept0.748
  A hypothesized intermediate-level linearly-represented feature (e.g., Beijing and China are closely associated) that may correlate with truth in unnegated datasets but anti-correlate in negated ones
• feature as applicationconcept0.745
  Metaphor treating each system feature or function as a separate application that can be independently loaded and managed.
• Feature Universalityconcept0.745
  Property of features that form consistently across different models trained on the same or similar data, suggesting features are real representational units
• Feature Visualizationmethod0.739
  Method of optimizing input to cause a neuron to fire maximally, used to characterize what a neuron detects; establishes causal link
• The features are often organized in geometrically-related clusters that share a semantic relationship.claim0.731
  Decoder cosine similarity maps onto concept similarity.