concept
active
concept:computation-in-superpositionComputation in superposition
More computations than neurons/dimensions.
Neighborhood — ranked by edge-count
Papers (1)
paper
Concepts (1)
concept
- Superpositionrelated_toPhenomenon where models represent more features than dimensions via almost-orthogonal directions.
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.
- Any method enabling enumeration of features.
- Specific phrases or sequences memorized via binary features in superposition, enabling narrow pattern matching despite few neurons
- Theoretical model of how neural networks encode more features than dimensions, informing linear representation work.
- Virtual weights between features forced into superposition by low-dimensional projections.
- Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
- Attentional features spread across multiple heads.
- Graph with edges (Wi·Wj)^2 to visualize interference.
- The state in which a dialogue agent maintains multiple possible characters simultaneously, refined as the conversation proceeds