Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Models
We introduce methods for discovering and applying sparse feature circuits. These are causally implicated subnetworks of human-interpretable features for explaining language model behaviors. Circuits identified in prior work consist of polysemantic and difficult-to-interpret units like attention heads or neurons, rendering them unsuitable for many downstream applications. In contrast, sparse feature circuits enable detailed understanding of unanticipated mechanisms. Because they are based on fine-grained units, sparse feature circuits are useful for downstream tasks: We introduce SHIFT, where we improve the generalization of a classifier by ablating features that a human judges to be task-irrelevant. Finally, we demonstrate an entirely unsupervised and scalable interpretability pipeline by discovering thousands of sparse feature circuits for automatically discovered model behaviors.
Code (2)
Tasks
Language ModelingLanguage ModellingSimilar Papers 제목 키워드 기반
Protein Circuit Tracing via Cross-layer Transcoders
Protein language models (pLMs) have emerged as powerful predictors of protein structure and function. However, the computational circuits underlying their predictions remain poorly understood. Recent mechanistic interpre…
Protein DesignSLIM: Sparse Latent Steering for Interpretable and Property-Directed LLM-Based Molecular Editing
Large language models possess strong chemical reasoning capabilities, making them effective molecular editors. However, property-relevant information is implicitly entangled across their dense hidden states, providing no…
Transcoders Find Interpretable LLM Feature Circuits
A key goal in mechanistic interpretability is circuit analysis: finding sparse subgraphs of models corresponding to specific behaviors or capabilities. However, MLP sublayers make fine-grained circuit analysis on transfo…
Sparse Autoencoders Enable Scalable and Reliable Circuit Identification in Language Models
This paper introduces an efficient and robust method for discovering interpretable circuits in large language models using discrete sparse autoencoders. Our approach addresses key limitations of existing techniques, name…
SCOUT: Semantic Concept Discovery for Open-Vocabulary Editing of face Recognition Templates
Face recognition templates are compact identity representations, yet they also encode rich semantic information about facial appearance. Prior work has shown that templates can be inverted to images or indirectly manipul…
Face Recognition