framework
active
framework:quantization-quanta-model-of-neural-scalingQuantization (quanta) model of neural scaling
Features analogous to quanta.
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Link to prior work.
Frameworks (1)
framework
- SAE latent allocation modelanalogous_toReduces SAE optimization to allocating N latents across features.
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.
- The central hypothesis of the paper; the platonic representation hypothesis itself
- The paper's central thesis statement, presented prominently after the abstract
- Working definition adopted by the paper.
- Demonstrated CNN representations predict neurons in visual cortex; background motivation for neural-network-brain correspondence.
- Primary empirical claim of the paper
- Mirrors real networks.