paper:vig-2020-investigatingInvestigating Gender Bias in Language Models Using Causal Mediation Analysis
Similar preprints — Semantic Scholar
Cited by (6)
- Stochastic Parameter Decomposition
Rank-one subcomponents trained against stochastic ablation masks recover ground-truth mechanisms in toy networks that Attribution-based Parameter Decomposition (APD) could not decompose, while removin
- Mixing Mechanisms: How Language Models Retrieve Bound Entities In-Context
Language models retrieve bound entities through a mixture of three mechanisms, not the positional mechanism alone, and the positional signal collapses in the middle of long entity lists. With n=20 ent
- pyvene: A Library for Understanding and Improving PyTorch Models via Interventions
pyvene is an open-source Python library that unifies intervention-based research on PyTorch neural models by treating the intervention itself—rather than model surgery code—as the primitive abstractio
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks
CausalGym, a benchmark derived from SyntaxGym's 33 test suites and expanded to 29 tasks, establishes that distributed alignment search (DAS) consistently outperforms linear probing, difference-in-mean
- The Geometry of Truth: Emergent Linear Structure in Large Language Model Representations of True/False Datasets
At sufficient scale, LLMs linearly represent the truth or falsehood of factual statements in their internal activations — a claim supported by PCA visualizations, cross-dataset probe transfer, and cau
- Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior
Manifold steering — intervening on model activations along paths constrained to lie on a learned activation manifold M_h rather than along Euclidean linear directions — produces behavioral trajectorie