hypothesis
active
hypothesis:with-sparse-kernels-causal-crosscoders-may-beat-per-layer-saes-on-flops

With sparse kernels, causal crosscoders may beat per-layer SAEs on FLOPs

Decoder cost dominates.

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.