finding
active
finding:turn-averaged-sae-trains-in-1-5-hours-on-4-h100-with-1-58m-samples-versus-266m-tokens-per-token

Turn-averaged SAE trains in ~1.5 hours on 4×H100 with ~1.58M samples versus 266M tokens per-token

Training efficiency.

Source paper

extracted_from
Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution
(2026) · Kevin Der · Harish Kamath · Thompson, Ben

Neighborhood — ranked by edge-count

Related by similarity (8)

cosine ≥ 0.65 · no typed edge

Entities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.