Attribution graph tracing information flow across parameter subcomponents for specific model predictions (e.g., 'her' vs 'his' pronoun selection)

{
  "doc": "paper.md",
  "context": "Shows how VPD-identified subnetworks can be analyzed to reveal interpretable pathways of computation (e.g., gender signal routing, syntactic role detection).",
  "norm_label": "Attribution graph tracing information flow across parameter subcomponents for specific model predictions (e.g., 'her' vs 'his' pronoun selection)",
  "graphify_id": "subnetwork_attribution",
  "source_file": "paper.md",
  "imported_from": "/Users/antonborzov/Documents/Research.nosync/papers/extract_typed_out/paper/graph.json",
  "extracted_type": "finding",
  "source_location": "§2.3",
  "graphify_file_type": "finding"
}