concept
active
concept:verbalizable-representationsVerbalizable representations
Representations poised to be verbalized.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Gurnee et al.'s privileged set of verbalisable representations behaving as a within-pass global workspace.
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.
- The central question of whether representational geometry implies corresponding computational structure
- The idea that features are encoded as directions in activation space.
- A representation that maintains stable activation across many tokens rather than being locally triggered by specific content
- Hierarchical representations in neural networks that allow compression and coordinated behaviour while retaining sensitivity to input changes.
- How a neural network encodes a semantic concept internally, argued to be better captured by manifolds than by atomic features.
- Adjacent ML literature on separating independent factors of variation; related to but distinct from the polysemanticity problem studied here
- Graph structure inferred purely in-context.
- Corroborated by reflection training.