framework
active
framework:disentangled-representationsDisentangled Representations
Adjacent ML literature on separating independent factors of variation; related to but distinct from the polysemanticity problem studied here
Neighborhood — ranked by edge-count
Concepts (1)
concept
- Polysemantic Neuronassociated_withA neuron that responds to multiple unrelated inputs, posing a major challenge for circuit-level interpretation
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- CIMC's characterization of part of the solution to the Hard Problem: insight into the structural necessities of phenomenal representation
- Related research agenda seeking representations that separate conceptually distinct factors; contrasted with superposition approach
- The central question of whether representational geometry implies corresponding computational structure
- Idea that information is spread across many neurons; superposition is a subtype.
- Hierarchical representations in neural networks that allow compression and coordinated behaviour while retaining sensitivity to input changes.
- Representations of one's own mental states; associated with consciousness in higher-order theories.
- The distribution of latent representations produced by the model under unperturbed inputs
- The idea that features are encoded as directions in activation space.