finding
active
finding:blocking-attention-to-query-token-in-layers-11-16-drops-accuracy-from-98-to-37-with-next-token-8

Blocking attention to query token in layers 11–16 drops accuracy from 98% to 37%; with next token 8%

Attention knockout.

Source paper

extracted_from
Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
(2025) · Yoav Gur-Arieh · Mor Geva · Atticus Geiger

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.