通过探针提示实现自动化归因图解释
Automated Attribution Graph Interpretation via Probe Prompting
AI总结：
提出探针提示方法，利用跨提示激活签名将归因图特征分组为概念对齐的超节点，并通过因果干预验证标签，在Gemma-2-2B上实现100%的预测转向行为。
摘要：
尽管我们知道从大型语言模型（LLM）输入到输出的精确计算过程，但这种计算仍然很难解释。使这一过程更易于理解的一种方法是创建一个稀疏计算图，该图以最少的计算节点捕获模型的大部分行为。跨层转码器（CLT）分解了MLP的密集计算，但即使对于短提示，生成的电路仍然包含数千个节点。现有的自动解释方法根据语料库激活对单个特征进行标记，但这些标记通常未经因果干预验证。我们引入了探针提示，这是一种透明的基于规则的流水线，它根据特征在一小组针对概念的探针提示上的响应，将归因图的特征分组为概念对齐的超节点，这些响应总结为跨提示激活签名（CPAS）。在四个事实领域，使用Gemma-2-2B和公共CLT词典以及45,596次实体交换干预，我们发现标记的超节点在每一次干预中都具有预测的转向行为。代码、数据集和交互式演示以匿名方式发布，作为可重复使用的工具，用于根据因果干预校准超节点标签。
英文摘要：
Even though we know the precise computations that lead from a large language model (LLM) input to its output this computation remains very hard to interpret. One way to make it easier to understand this process is by creating a sparse computational graph that captures most of the model behavior with smallest number of computational nodes. Cross-layer transcoders (CLT) decompose the dense computations of the MLP but the resulting circuits still contain thousands of nodes even for short prompts. Existing automated interpretation methods label individual features from corpus activations, and it often happens that these labels are not validated by causal intervention. We introduce probe prompting, a transparent rule-based pipeline that groups the features of an attribution graph into concept-aligned supernodes from their responses on a small set of concept-targeted probe prompts, summarized as Cross-Prompt Activation Signatures (CPAS). Across four factual domains, on Gemma-2-2B with a public CLT dictionary and 45,596 entity-swap interventions, we find that the labeled supernodes have the predicted steering behavior in every one of them. Code, datasets, and an interactive demo are released anonymously as a reusable harness for calibrating supernode labels against causal interventions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
