Have Faith in Faithfulness: Going Beyond Circuit Overlap When Finding Model Mechanisms
This work addresses the scalability and faithfulness challenges in interpretability for language model researchers, offering an incremental improvement over existing methods.
The paper tackles the problem of identifying faithful computational subgraphs (circuits) in language models by introducing EAP-IG, a method that improves faithfulness over existing gradient-based approximations, showing that circuits found with EAP-IG are more faithful than those from EAP despite similar node overlap.
Many recent language model (LM) interpretability studies have adopted the circuits framework, which aims to find the minimal computational subgraph, or circuit, that explains LM behavior on a given task. Most studies determine which edges belong in a LM's circuit by performing causal interventions on each edge independently, but this scales poorly with model size. Edge attribution patching (EAP), gradient-based approximation to interventions, has emerged as a scalable but imperfect solution to this problem. In this paper, we introduce a new method - EAP with integrated gradients (EAP-IG) - that aims to better maintain a core property of circuits: faithfulness. A circuit is faithful if all model edges outside the circuit can be ablated without changing the model's performance on the task; faithfulness is what justifies studying circuits, rather than the full model. Our experiments demonstrate that circuits found using EAP are less faithful than those found using EAP-IG, even though both have high node overlap with circuits found previously using causal interventions. We conclude more generally that when using circuits to compare the mechanisms models use to solve tasks, faithfulness, not overlap, is what should be measured.