framework
active
framework:cross-layer-transcoders

Cross-Layer Transcoders

MLP replacement with sparse features underlying the original attribution graphs.

Neighborhood — ranked by edge-count

Methods (4)

method
  • Gradient-based technique using SAE features to estimate causal effects on completions; used to corroborate NLA findings.
  • Decomposition method for activations; VPD is compared against transcoders in sparsity-reconstruction tradeoff.
  • CLT plus error nodes and original attention patterns, local to a prompt.
  • Substitutes all MLP outputs with CLT reconstructions.

Frameworks (2)

framework

Artifacts (1)

artifact

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.