concept
active
concept:principal-component-analysisPrincipal Component Analysis
Linear-model solution that trades off with superposition.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionmentions
Concepts (1)
concept
- Superpositionanalogous_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.
- Statistical method used to analyze neural activity data.
- Used to visualize LLM true/false representations, revealing clear linear structure separating true from false statements
- Method used by Lu et al. to find orthogonal directions of maximum variance among 275 character archetypes in activation space
- PCA components treated as SAE latents for comparison.
- Used to visually inspect separation of truth-related directions in model activation space across layers
- Method comparing brain activity in conscious vs. unconscious conditions.
- Engineering simulation used from the earliest stage to develop the syncopated structural grid for large buildings.
- Cosine similarity at lags to test stationarity.