Pinned Repositories
ai-psychosis
ARENA_3.0
trying to fix a typo
bilinear-feature-circuits
Let's try do some sparse feature circuits with bilinear models.
bilinear_interp_tim
Tim doing bilinear interp
bloom-evals
Fork of blom evals
combining_monitors_public
crosscoder_fun
Do crosscoder but for pythia checkpoints
ECON-1011A-Textbook
A textbook for Professor Edward Glaeser's ECON 1011A: Microeconomic Theory - Advanced, course at Harvard.
inspect_evals
Collection of evals for Inspect AI
tim-hua-01.github.io
Website
tim-hua-01's Repositories
tim-hua-01/ai-psychosis
tim-hua-01/ECON-1011A-Textbook
A textbook for Professor Edward Glaeser's ECON 1011A: Microeconomic Theory - Advanced, course at Harvard.
tim-hua-01/tim-hua-01.github.io
Website
tim-hua-01/ARENA_3.0
trying to fix a typo
tim-hua-01/bilinear-feature-circuits
Let's try do some sparse feature circuits with bilinear models.
tim-hua-01/bilinear_interp_tim
Tim doing bilinear interp
tim-hua-01/bloom-evals
Fork of blom evals
tim-hua-01/combining_monitors_public
tim-hua-01/crosscoder_fun
Do crosscoder but for pythia checkpoints
tim-hua-01/evalplus
Rigourous evaluation of LLM-synthesized code - NeurIPS 2023 & COLM 2024
tim-hua-01/inspect_evals
Collection of evals for Inspect AI
tim-hua-01/SAE_Error_probes
Place to save experiments
tim-hua-01/tim-hua-01
Config files for my GitHub profile.
tim-hua-01/sandbagging_eval
Code and data for "Systematic Sandbagging Evaluations on Claude 3.5 Sonnet"
tim-hua-01/Test_Awareness_Steering
Code for the paper: Linear Control of Test Awareness Reveals Differential Compliance in Reasoning Models
tim-hua-01/Unsupervised-Elicitation-tim