finding
active
finding:per-token-sae-achieves-per-token-nmse-0-162-best-of-all-modelsPer-token SAE achieves per-token nMSE 0.162, best of all models
Table 1.
Source paper
extracted_from(2026) · Kevin Der · Harish Kamath · Thompson, Ben
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.
- Table 1.
- Table 1.
- Table 1.
- Table 1.
- Standard baseline SAE operating on individual token activations.
- Table 1 on Qwen-2.5-7B holdout.
- Basic SAE performance metrics.
- The specific SAE architecture trained: 100K+ possible features compressed to 64 active per token for layer-40 activations