claim
active
claim:moving-from-saes-modeling-representation-to-transcoders-modeling-computation-makes-unfaithful-mechanisms-possible-even-with-monosemantic-low-mse-features

Moving from SAEs modeling representation to transcoders modeling computation makes unfaithful mechanisms possible even with monosemantic, low-MSE features

Core motivation.

Source paper

extracted_from
A Toy Model of Mechanistic (Un)Faithfulness
Chris Olah

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.