hypothesis
active
hypothesis:if-all-of-2-retained-weights-were-interpretable-the-result-would-be-closer-to-an-upstairs-lift

If all of ~2% retained weights were interpretable, the result would be closer to an 'upstairs' lift

Speculative possibility.

Source paper

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

Neighborhood — ranked by edge-count

Findings (1)

finding

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.