concept
active
concept:sae-scaling-lawsSAE scaling laws
Loss follows a power law in the number of latents.
Neighborhood — ranked by edge-count
Papers (1)
paper
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.
- Sweeping number of features and training steps to find compute-optimal SAE configurations.
- Observation that SAE loss decreases as a power law with compute budget.
- Hypothesis cited in paper suggesting deceptive capabilities may scale with model size
- Left open.
- Link to prior work.
- Compute-optimal hyperparameters follow predictable power-law relationships.
- Mechanisms by which smaller competent subunits bind into a higher-level Self with larger goals; key example via gap junction connections.
- Techniques that leverage AI to help humans more efficiently supervise AI.