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.

翻译：近期许多语言模型（LM）可解释性研究采用了电路框架，旨在寻找解释LM在特定任务上行为的最小计算子图（即电路）。多数研究通过独立对每条边进行因果干预来确定LM电路中应包含哪些边，但这种方法随模型规模扩大扩展性较差。边缘归因修补（EAP）作为一种基于梯度的干预近似方法，已成为该问题的可扩展但非完美解决方案。本文提出一种新方法——基于积分梯度的EAP（EAP-IG）——旨在更好地维护电路的核心属性：忠实性。如果模型电路外的所有边在消融后不影响模型在任务上的性能，则该电路是忠实的；忠实性正是研究电路而非完整模型的正当理由。实验表明，使用EAP发现的电路忠实性低于使用EAP-IG发现的电路，尽管两者与先前通过因果干预发现的电路在节点重叠度上均较高。我们得出更普遍性结论：当利用电路比较模型解决任务所用的机制时，应衡量的是忠实性而非重叠度。