finding
active
finding:1-0-balances-nested-loss-terms-avoiding-degradation-at-either-end-of-the-0-25-4-0-sweep

α=1.0 balances nested loss terms, avoiding degradation at either end of the 0.25–4.0 sweep

Alpha sweep.

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.