Independent researcher | Mechanistic Interpretability, AI safety
-
22:32
(UTC +08:00) - in/yi-wen-chu-9b5b662b3
Pinned Loading
-
ARENA_MI
ARENA_MI PublicRespository for personal project and experiments base on ARENA Mechanistic Interpretability curriculum
HTML
-
SAE-Jailbreak-Research
SAE-Jailbreak-Research PublicRepository for SAE detect and fix Jailbreak on LLM research
Jupyter Notebook
-
Zero_to_Hero
Zero_to_Hero Public(2023 Project) I followed the online course "Neural Networks: Zero to Hero" by Andrej Karpathy", Built a GPT-2-level language model from scratch using Python, this help me gain a through undersdand…
Jupyter Notebook
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.