arxiv:2510.02292
Shuyu Wu
wonderwind271
AI & ML interests
LLM (pre)training dynamics; Mechanistic Interpretability
Recent Activity
published
a dataset
about 22 hours ago
compling/event_factuality
published
a dataset
1 day ago
compling/somo
liked
a model
26 days ago
meta-llama/Llama-3.1-8B
Organizations
models
16
wonderwind271/gpt2_scrub1
Text Generation
•
0.1B
•
Updated
•
21
wonderwind271/gpt2-probe-finetune-UD-L4
Text Generation
•
0.1B
•
Updated
•
5
wonderwind271/childes-checkpoints
Updated
wonderwind271/childes-probing-tunedlens
Updated
wonderwind271/vsdiag-checkpoints
Updated
wonderwind271/gpt2-vsdiag-1
Text Generation
•
0.1B
•
Updated
•
2
wonderwind271/gpt2-childes-v4
Text Generation
•
0.2B
•
Updated
•
1
wonderwind271/gpt2-childes-v2
Text Generation
•
0.2B
•
Updated
wonderwind271/gpt2-childes-v1
Text Generation
•
0.1B
•
Updated
wonderwind271/gpt2-ACL-series
Text Generation
•
0.1B
•
Updated
datasets
18
wonderwind271/PKU-SafeRLHF-transformed
Viewer
•
Updated
•
12k
•
18
wonderwind271/en_gum-ud-train
Viewer
•
Updated
•
7.79k
•
4
wonderwind271/en_gum-ud-test
Viewer
•
Updated
•
1.19k
•
3
wonderwind271/en_gum-ud-dev
Viewer
•
Updated
•
1.23k
•
5
wonderwind271/en_ewt-ud-train
Viewer
•
Updated
•
8.04k
•
4
wonderwind271/en_ewt-ud-test
Viewer
•
Updated
•
1.09k
•
7
wonderwind271/en_ewt-ud-dev
Viewer
•
Updated
•
1.03k
•
4
wonderwind271/Hi-ToM
Viewer
•
Updated
•
1.2k
•
6
wonderwind271/wikipedia-selection-512w
Viewer
•
Updated
•
940k
•
17
wonderwind271/wikipedia-selection
Viewer
•
Updated
•
1M
•
16