method
active
method:sparse-decomposition-by-gradient-pursuitSparse decomposition by gradient pursuit
Used to compute J-space components and occupancy.
Neighborhood — ranked by edge-count
Papers (1)
paper
Methods (1)
method
- Jacobian LensusesGurnee et al.'s interpretability method used to identify the J-space workspace.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- Used for updating hidden state expectations; provides dynamical process theory testable against neuronal data
- Method from Gurnee et al. 2023 for finding feature directions including individual neuron analysis
- Optimization technique that computes weight changes by following the gradient of an error function; contrasted with evolutionary stochastic search.
- 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