1
Reading Task Failure Off the Activations: A Sparse-Feature Audit of GPT-2 Small on Indirect Object Identification
GPT-2小模型在间接宾语识别任务中的失败与成功，稀疏特征差异揭示模型内部行为，一次小而透明的审计。
arXiv:2605.22719v1 Announce Type: new Abstract: We report a small, reproducible audit of which sparse-autoencoder (SAE) features of GPT-2 small fire d…