framework
active
framework:absolute-value-computation-modelAbsolute value computation model
Model computing abs(x) in superposition.
Neighborhood — ranked by edge-count
Papers (1)
paper
- Toy Models of Superpositionintroducesmentions
Frameworks (1)
framework
- ReLU hidden layer toy modelextendsToy model with privileged basis.
Findings (1)
finding
- Limitation of that toy model.
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.
- Absolute value model (n=100, m=40) computes abs in superposition when features are sparsefinding0.794Computation in superposition.
- Mechanistic motif.
- Statistical technique where outputs are regressed on previous values; used in language generation
- Without superposition.
- Second model system studied; used to show why flat autoregressive LLMs struggle with long-range coherence.
- The computational approach used to simulate morphogenesis with cells as agents on a 2D grid; allows quantitative testing of stress-sharing hypothesis.
- Class of large language models designed to produce extended chain-of-thought before answering, studied in this paper