method
active
method:sparse-decomposition-by-gradient-pursuit

Sparse decomposition by gradient pursuit

Used to compute J-space components and occupancy.

Neighborhood — ranked by edge-count

Methods (1)

method
  • Gurnee et al.'s interpretability method used to identify the J-space workspace.

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.

  • Gradient Descentmethod0.756
    Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data
  • Sparse Probingmethod0.751
    Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
  • Gradient methodmethod0.747
    Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.
  • k-Sparse Probingmethod0.745
    Concept detection metric using top-k latents and linear probe.
  • General method for finding overcomplete sparse decompositions; the paper uses sparse autoencoders as an approximation
  • The extracted set of sparse interpretable features from model embeddings via SAEs
  • Primary method introduced: trains a one-hidden-layer MLP with L1 sparsity penalty to decompose model activations into overcomplete feature dictionaries
  • Mechanistic finding by Bricken et al. 2023 about how LLMs store features; cited as operational justification for pattern-repository assumption