framework
active
framework:crosscoders

Crosscoders

Learn a shared feature space across two models; basis of the work.

Neighborhood — ranked by edge-count

Methods (2)

method
  • General method for finding overcomplete sparse decompositions; the paper uses sparse autoencoders as an approximation
  • Post-hoc metric for model exclusivity in standard crosscoders.

Frameworks (4)

framework

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.

  • Transcodersmethod0.859
    Decomposition method for activations; VPD is compared against transcoders in sparsity-reconstruction tradeoff.
  • Transcodermethod0.845
    Uses activations from one layer to predict the next; special case of crosscoders.
  • Sparse dictionary learning variant that reads and writes to multiple layers or models, yielding shared features.
  • Basic crosscoder reading and reconstructing all layers jointly.
  • Mask virtual weights during training targeting interference.
  • Used to express MLP in monosemantic features, 4096 features with JumpReLU.
  • Each feature assigned a window of K layers to reduce training FLOPs.
  • Train a single SAE encoding and decoding activations from two models simultaneously to find shared and exclusive features.