Toward a Theory of Generalizability in LLM Mechanistic Interpretability Research
"机制解释" 相关文章
Towards scientific discovery with dictionary learning: Extracting biological concepts from microscopy foundation models
Tracing Facts or just Copies? A critical investigation of the Competitions of Mechanisms in Large Language Models
The REPHRASE Circuit: How Fine-Tuning Enhances LLMs to REPHRASE Text
一个被长期忽视的因素，对乳腺癌治疗效果有重要影响
