method
active
method:l1-of-norms-regularization

L1-of-norms regularization

Sparsity penalty weighting by sum of per-layer decoder norms, enabling comparability with per-layer SAEs.

Neighborhood — ranked by edge-count

Methods (2)

method
  • L2-of-norms regularization
    contradictsrelated_to
    Alternative penalty that spreads features across layers and finds only shared features.
  • Sparse dictionary learning variant that reads and writes to multiple layers or models, yielding shared features.

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.