concept
active
concept:feature-disentanglement

Feature Disentanglement

Independent concepts are encoded by separate latents.

Neighborhood — ranked by edge-count

Methods (3)

method

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.

  • Disentanglementframework0.847
    Related research agenda seeking representations that separate conceptually distinct factors; contrasted with superposition approach
  • CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation
  • Adjacent ML literature on separating independent factors of variation; related to but distinct from the polysemanticity problem studied here
  • Feature splittingconcept0.808
    Phenomenon where a feature in a small SAE splits into multiple finer features in a larger SAE.
  • Explains inverse scaling.
  • SAE-derived representation space where individual dimensions activate for distinct concepts, enabling cleaner steering
  • Problems suggesting sparsity breaks down as interpretability proxy.
  • Feature Sparsityconcept0.758
    Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work