找出GPT-2小模型中负责动词变位的神经回路。
Identifying a Circuit for Verb Conjugation in GPT-2
- 通过路径修补和逻辑归因定位关键子网络。
- 仅需少量组件对即可实现接近模型性能的动词变位。
- 适合对大模型可解释性感兴趣的读者。
本文实现了一种方法，用于隔离并解读GPT-2 Small中负责主谓一致的子网络（或称“电路”）。实验中，模型接收主语为单数（如“Alice”）或复数（如“Alice and Bob”）的提示，任务是正确预测动词形式（单数用“walks”，复数用“walk”）。通过一系列技术——包括性能验证、基于直接路径修补的自动电路发现，以及直接逻辑归因——成功识别出一个对正确动词变位有显著贡献的候选电路。结果表明，仅需极小部分的网络组件-标记对，即可在基础任务上达到接近模型性能的表现；但在更复杂场景下，则需要更多组件。该研究揭示了语言任务在模型中的局部化实现机制。
原文摘要 · Abstract (English)
I implement a procedure to isolate and interpret the sub-network (or "circuit") responsible for subject-verb agreement in GPT-2 Small. In this study, the model is given prompts where the subject is either singular (e.g. "Alice") or plural (e.g. "Alice and Bob"), and the task is to correctly predict the appropriate verb form ("walks" for singular subjects, "walk" for plural subjects). Using a series of techniques-including performance verification automatic circuit discovery via direct path patching, and direct logit attribution- I isolate a candidate circuit that contributes significantly to the model's correct verb conjugation. The results suggest that only a small fraction of the network's component-token pairs is needed to achieve near-model performance on the base task but substantially more for more complex settings.
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。