finding
active
finding:attribution-graph-tracing-information-flow-across-parameter-subcomponents-for-specific-model-predictions-e-g-her-vs-his-pronoun-selectionAttribution graph tracing information flow across parameter subcomponents for specific model predictions (e.g., 'her' vs 'his' pronoun selection)
Shows how VPD-identified subnetworks can be analyzed to reveal interpretable pathways of computation (e.g., gender signal routing, syntactic role detection).
Source paper
extracted_fromNeighborhood — ranked by edge-count
Communities (4)
community
- Spans attention head decomposition, benchmark awareness, and genomic pathogenicity prediction via neural models.
- Tracing information flow through weight matrices and attention heads using attribution graphs to identify causally important subcomponents in language models.
- Tracing information flow through parameter subcomponents to isolate computational mechanisms for specific model predictions, using tools like attribution graphs and VPD.
- Mechanistic tracing of information flow through attention and MLP subcomponents for pronoun prediction tasks
Methods (1)
method
- Core technique introduced in this paper for decomposing neural network weight matrices into mechanistically simple, interpretable rank-one subcomponents.
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.
- Gradient-based technique using SAE features to estimate causal effects on completions; used to corroborate NLA findings.
- Quantifies method limitations.
- Attribution graph reveals a pathway that detects the verb 'lost' and upweights object pronounsfinding0.793Second component of the subnetwork for 'her', complementing the femaleness signal.
- Motivates 14-turn case.
- Mechanistic discrimination of CoT faithfulness.
- Contrast in §6.3.
- Some gradient-based attribution methods give attributions independent of model and data-generating processfinding0.769Adebayo et al. sanity checks.
- Detailed case study demonstrating how VPD subnetworks can be traced to reveal multiple interpretable computational pathways for a single prediction.