AI 中文总结
介绍CircuitKIT工具包，用于机理可解释性的电路分析。它通过可序列化表示连接工作流程，提供发现算法、声明式接口、电路诊断及应用模块，为电路分析提供通用基础设施，解决了现有方法碎片化问题。
AI 中文摘要
电路分析不仅能支持模型解释，还能用于下游干预，如剪枝、编辑、引导和选择性微调。然而，当前进行此类分析需要拼凑发现、评估和干预的单独实现，还需手动编写许多发现方法所需的对比提示。这种碎片化使得方法难以比较，并限制了其在规范任务之外的应用。我们引入了CircuitKIT，一个通过类型化、可序列化表示连接电路分析工作流程的开源库。CircuitKIT提供了一套发现算法、将结构化数据映射到发现任务的声明式接口、互补的电路诊断和下游应用模块。这些组件共同为进行和比较电路分析提供了通用基础设施。该库、示例、笔记本和文档可在给定的https URL上获取。
英文摘要
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 .
