Sparse dictionary learning has been a rapidly growing technique in mechanistic interpretability to attack superposition and extract more human-understandable features from model activations. We ask a further question based on the extracted more monosemantic features: How do we recognize circuits connecting the enormous amount of dictionary features? We propose a circuit discovery framework alternative to activation patching. Our framework suffers less from out-of-distribution and proves to be more efficient in terms of asymptotic complexity. The basic unit in our framework is dictionary features decomposed from all modules writing to the residual stream, including embedding, attention output and MLP output. Starting from any logit, dictionary feature or attention score, we manage to trace down to lower-level dictionary features of all tokens and compute their contribution to these more interpretable and local model behaviors. We dig in a small transformer trained on a synthetic task named Othello and find a number of human-understandable fine-grained circuits inside of it.

基于稀疏字典学习和机制解释性，提出了一种电路发现框架，用于从模型激活中提取更多人可理解的特征。该框架能够识别连接大量字典特征的电路，并在渐近复杂度方面具有更高的效率。在合成任务 Othello 的小型 Transformer 中，发现了许多人可理解的细粒度电路。

字典学习改善机械解释性中无补丁电路发现：以奥赛罗-GPT为例