首次获取该候选人的完整档案及 StartLux 评估共 20 积分；每位用户单独解锁，之后查看免费。主动刷新 20 积分。
实时查找电子邮箱，费用不超过20积分；未找到邮箱不扣费。
Amrith Setlur · Matthew Yang · Charlie Snell · Jeremiah Greer · Ian Wu · Virginia Smith · Max Simchowitz · Aviral Kumar
Xiangchen Song · Aashiq Muhamed · Yujia Zheng · Lingjing Kong · Zeyu Tang · Mona T. Diab · Virginia Smith · Kun Zhang
Sparse Autoencoders (SAEs) are a prominent tool in mechanistic interpretability (MI) for decomposing neural network activations into interpretable features. However, the aspiration to identify a canonical set of features is challenged by the observed inconsistency of learned SAE features across d...