jasonlim131 Goto Github PK

arena_replication

Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

coopai

For Learning in Symmetric Teams, Local Optima are Global Nash Equilibria

copycat

Modern port of Melanie Mitchell's and Douglas Hofstadter's Copycat

courses-1

Code from university courses.

credit-scoring

Implement supervised machine learning techniques in order to further understanding the process in which a client will be granted a credit and be denied a credit.

deduct

goal-misgen-implicit

replication of Dorn et al.'s paper

grok-1

Grok Opensource Repo for Familiarization with Large Mixtral LLMs

mats_deduct

a MATS project application for mechanistic interpretability stream

maze_rl_peek

multimodal-gamer

A framework to enable multimodal models to play games on a computer.

notes

Markdown files for the linked-blog-starter repository

pokemonredrl

Playing Pokemon Red with Reinforcement Learning

pytorch_hippocampus_fast_learning

Attempt to Model Rhesus Macaques' Hippocampal Pathway using PyTorch

sae_gpt2_small

Replication of dictionary learning in gpt2-small

self-operating-computer

A framework to enable multimodal models to operate a computer.

slate

Final project for CIS 4120/5120 @ Penn

sparse_ae

Sparse Autoencoder for Mechanistic Interpretability for Practice

speechbci_v1

valence_prediction_4290

Predict emotional valence from EEG using machine learning