註冊並分享邀請連結,可獲得影片播放與邀請獎勵。

Thomas Jiralerspong
@tomjiralerspong
PhD with Yoshua Bengio & Guillaume Lajoie, prev. research fellow with Anthropic, Google DeepMind
加入 November 2019
182 正在關注    996 粉絲
PSA to everyone doing neuron interp after the recent monosemantic neuron posts: the model's training recipe matters a lot. e.g. GPT2 seems to have been trained WITH dropout (modern LLMs are not), which seems to increase redundancy and (maybe) polysemanticity but reduce superposition (see sources in comments). Other choices probably also have an effect (e.g. SwiGLU vs GELU MLPs, optimizer, amount of weight decay, etc.) and I think we should be careful not to generalize too much. Currently working on a project to characterize the effects of these choices on neuron interpretability (a lot of the existing work is done on older/toy models which I'm not sure are representative), feel free to reach out if interested!
顯示更多
0
20
532
24
轉發到社區