quote
active
quote:interference-weights-are-one-of-the-stranger-implications-of-trained-models-approximating-high-dimensional-circuits-through-low-dimensional-bottlenecks

Interference weights are one of the stranger implications of trained models approximating high-dimensional circuits through low-dimensional bottlenecks

Concluding statement.

Source paper

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

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.