method
active
method:features-per-dimensionFeatures per dimension
Measure of superposition in toy models.
Neighborhood — ranked by edge-count
Papers (1)
paper
Frameworks (1)
framework
- Core theoretical framework: neural networks represent more features than neurons by encoding features as directions in superposition
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.
- Fraction of a dimension given to a feature.
- Measures features learned.
- Dual to discrete dictionary features; central frame.
- Research thread within About Blank concerning the structure and relational properties of neural network feature representations; covariance pooling tangentially supports this thread.
- Interpretable concept representations hypothesized as basic units of computation.
- Property that features activate on only a small fraction of inputs; enables compressed sensing and is what allows superposition to work
- Decomposability, linearity, superposition, basis alignment.
- General principle supported tangentially by covariance pooling work; relates to feature co-occurrence structure.