claim
active
claim:harmful-weights-reflect-the-tradeoff-between-implementing-more-or-more-complex-circuits-and-the-interference-between-them

Harmful weights reflect the tradeoff between implementing more or more complex circuits and the interference between them

Discussion.

Source paper

extracted_from
Characterizing interference weights in a tiny language model
Nicholas L. Turner · Jeffrey Wu · Joshua Batson

Neighborhood — ranked by edge-count

Concepts (1)

concept
  • Logit weight contributions from a feature that arise due to superposition with other features, not from the feature's own causal role

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.