framework
active
framework:hierarchy-of-feature-propertiesHierarchy of feature properties
Decomposability, linearity, superposition, basis alignment.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionintroducesmentions
Frameworks (1)
framework
- The hypothesis that models internalize concepts as approximately linear directions in representation space; used to interpret MDS injection behavior
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.
- An ordering of texts via spatial cues like indentation, size, and placement, implying importance.
- Fraction of a dimension given to a feature.
- Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
- Measure of superposition in toy models.
- Interpretable concept representations hypothesized as basic units of computation.
- Synthesizing inputs maximizing component activation.
- Complex, behavior-level semantic attributes such as personality traits that the paper aims to steer.
- Premise that models represent concepts as features.