arxiv:2510.02292
Shuyu Wu
wonderwind271
AI & ML interests
LLM (pre)training dynamics; Mechanistic Interpretability
Recent Activity
updated
a dataset
5 days ago
HappyEval/SWE-bench-embedding
published
a dataset
5 days ago
HappyEval/SWE-bench-embedding
updated
a dataset
5 days ago
HappyEval/gsm8k-embedding
Organizations
models
14
wonderwind271/childes-checkpoints
Updated
wonderwind271/childes-probing-tunedlens
Updated
wonderwind271/vsdiag-checkpoints
Updated
wonderwind271/gpt2-vsdiag-1
Text Generation
•
0.1B
•
Updated
•
3
wonderwind271/gpt2-childes-v4
Text Generation
•
0.2B
•
Updated
•
3
wonderwind271/gpt2-childes-v2
Text Generation
•
0.2B
•
Updated
•
3
wonderwind271/gpt2-childes-v1
Text Generation
•
0.1B
•
Updated
•
4
wonderwind271/gpt2-ACL-series
Text Generation
•
0.1B
•
Updated
•
5
wonderwind271/wordlevel-tokenizer
Updated
wonderwind271/babylm-raw-tokenizer
Updated
datasets
11
wonderwind271/Hi-ToM
Viewer
•
Updated
•
1.2k
•
16
wonderwind271/wikipedia-selection-512w
Viewer
•
Updated
•
940k
•
17
wonderwind271/wikipedia-selection
Viewer
•
Updated
•
1M
•
73
wonderwind271/coco-val2017-obj-qa
Viewer
•
Updated
•
2.69k
•
6
wonderwind271/GQA_dataset
Viewer
•
Updated
•
2.01M
•
19
wonderwind271/CLEVR_val
Viewer
•
Updated
•
150k
•
9
wonderwind271/visualDialog-pretrain
Viewer
•
Updated
•
49.3k
•
17
wonderwind271/CHILDES-raw
Viewer
•
Updated
•
11.5M
•
33
wonderwind271/ACL-papers-truncated
Viewer
•
Updated
•
500
•
37
wonderwind271/ACL-papers
Viewer
•
Updated
•
8.55k
•
12