一站式电路分析工具，让模型可解释与干预更高效
CircuitKIT : Circuit Discovery, Evaluation, and Application Toolkit for Mechanistic Interpretability
- 用统一数据格式串联发现、评估、应用全流程
- 支持剪枝、编辑、微调等下游操作的电路干预
- 提供可复现的结构化接口，适合研究者快速实验
电路分析不仅能解释模型行为，还可用于剪枝、编辑、控制和选择性微调等下游干预。然而，当前方法需手动拼接不同模块，且多数发现方法依赖人工编写对比提示词，导致流程割裂，难以比较，应用也受限于典型任务。我们提出 CircuitKIT，一个开源库，通过类型化、可序列化的表示连接整个电路分析流程。该工具包包含多种发现算法、将结构化数据映射为发现任务的声明式接口、互补的电路诊断工具及下游应用模块。这些组件共同构建了可复现、可比较的电路分析基础设施。代码、示例、笔记本和文档已公开于 https://github.com/Lexsi-Labs/CircuitKIT。
原文摘要 · Abstract (English)
Circuit analysis can support not only model explanation but also downstream interventions such as pruning, editing, steering, and selective fine-tuning. However, conducting such analyses currently requires stitching together separate implementations for discovery, evaluation, and intervention, as well as hand-authoring the contrastive prompts required by many discovery methods. This fragmentation makes methods difficult to compare and limits their application beyond canonical tasks. We introduce CircuitKIT, a source-available library that connects the circuit-analysis workflow through a typed, serializable representation. CircuitKIT provides a suite of discovery algorithms, declarative interfaces for mapping structured data into discovery tasks, complementary circuit diagnostics, and downstream application modules. Together, these components provide common infrastructure for conducting and comparing circuit analyses. The library, examples, notebooks, and documentation are released at https://github.com/Lexsi-Labs/CircuitKIT .
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。