sparse autoencoders

{
  "doc": "paper.md",
  "context": "Existing method for model interpretability that decodes model activations rather than parameters themselves, noted as incomplete solution.",
  "category": "ai",
  "norm_label": "sparse autoencoders",
  "graphify_id": "sparse_autoencoders",
  "source_file": "paper.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/paper/graph.json",
  "extracted_type": "method",
  "source_location": "§1",
  "graphify_file_type": "method"
}