Activation patching is a standard method in mechanistic interpretability for localizing the components of a model responsible for specific behaviors, but it is computationally expensive to apply at scale. Attribution patching offers a faster, gradient-based approximation, yet suffers from noise and reduced reliability in deep, highly non-linear networks. In this work, we introduce Relevance Patching (RelP), which replaces the local gradients in attribution patching with propagation coefficients derived from Layer-wise Relevance Propagation (LRP). LRP propagates the network's output backward through the layers, redistributing relevance to lower-level components according to local propagation rules that ensure properties such as relevance conservation or improved signal-to-noise ratio. Like attribution patching, RelP requires only two forward passes and one backward pass, maintaining computational efficiency while improving faithfulness. We validate RelP across a range of models and tasks, showing that it more accurately approximates activation patching than standard attribution patching, particularly when analyzing residual stream and MLP outputs in the Indirect Object Identification (IOI) task. For instance, for MLP outputs in GPT-2 Large, attribution patching achieves a Pearson correlation of 0.006, whereas RelP reaches 0.956, highlighting the improvement offered by RelP. Additionally, we compare the faithfulness of sparse feature circuits identified by RelP and Integrated Gradients (IG), showing that RelP achieves comparable faithfulness without the extra computational cost associated with IG.

翻译：激活修补是机制可解释性中用于定位模型特定行为对应组件的标准方法，但其大规模应用的计算成本高昂。归因修补提供了一种基于梯度的快速近似方法，但在深度、高度非线性网络中易受噪声影响且可靠性降低。本研究提出相关性修补（RelP），该方法将归因修补中的局部梯度替换为源自层间相关性传播（LRP）的传播系数。LRP通过逐层反向传播网络输出，依据局部传播规则（如相关性守恒或信噪比提升）将相关性重新分配至底层组件。与归因修补类似，RelP仅需两次前向传播和一次反向传播，在保持计算效率的同时提升了忠实性。我们在多种模型和任务中验证RelP，结果表明其比标准归因修补更精确地逼近激活修补，尤其在分析间接宾语识别（IOI）任务中的残差流和MLP输出时表现突出。例如，在GPT-2 Large的MLP输出分析中，归因修补的皮尔逊相关系数为0.006，而RelP达到0.956，凸显了RelP的改进效果。此外，我们比较了RelP与积分梯度（IG）所识别稀疏特征电路的忠实性，显示RelP在未增加IG额外计算成本的情况下实现了相当的忠实性。