tim-hua-01
Follow
-
-
-
-
bloom-evals Public
Forked from safety-research/bloom-evalsFork of blom evals
Python MIT License UpdatedAug 30, 2025 -
sandbagging_eval Public
Forked from farrelmahaztra/sandbaggingCode and data for "Systematic Sandbagging Evaluations on Claude 3.5 Sonnet"
Python UpdatedAug 1, 2025 -
inspect_evals Public
Forked from UKGovernmentBEIS/inspect_evalsCollection of evals for Inspect AI
Python MIT License UpdatedJul 18, 2025 -
Unsupervised-Elicitation-tim Public
Forked from Jiaxin-Wen/Unsupervised-ElicitationPython UpdatedJun 17, 2025 -
Test_Awareness_Steering Public
Forked from microsoft/Test_Awareness_SteeringCode for the paper: Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models
Jupyter Notebook MIT License UpdatedJun 5, 2025 -
-
bilinear-feature-circuits Public
Forked from saprmarks/feature-circuitsLet's try do some sparse feature circuits with bilinear models.
Jupyter Notebook MIT License UpdatedFeb 13, 2025 -
bilinear_interp_tim Public
Forked from tdooms/bilinear-interpTim doing bilinear interp
Jupyter Notebook UpdatedFeb 12, 2025 -
crosscoder_fun Public
Forked from ckkissane/crosscoder-model-diff-replicationDo crosscoder but for pythia checkpoints
Jupyter Notebook UpdatedJan 23, 2025 -
-
evalplus Public
Forked from evalplus/evalplusRigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
Jupyter Notebook Apache License 2.0 UpdatedOct 22, 2024 -
ARENA_3.0 Public
Forked from callummcdougall/ARENA_3.0trying to fix a typo
HTML UpdatedJun 30, 2024 -
ECON-1011A-Textbook Public
Forked from TheKeveloper/ECON-1011A-TextbookA textbook for Professor Edward Glaeser's ECON 1011A: Microeconomic Theory - Advanced, course at Harvard.