Pinned Repositories
ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
brain-representations
character-sim-interp
cornell-ml-kaggle-winner
My winning submission (1st out of 155 participants) to Cornell's ML Kaggle competition
iti_capstone
Analyzing truth representations in LLMs across different kinds of truth and intervening on their hidden states to make LLMs more truthful
jamescampbell57.github.io
llama-lying
Code for our paper "Localizing Lying in Llama"
NLP-brain-biased-robustness
CS 6740 term project: "CereBERTo: Improving Distributional Robustness with Brain-Like Language Representations"
ProctorAI
The AI to keep you focused 😈
representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
jam3scampbell's Repositories
jam3scampbell/ProctorAI
The AI to keep you focused 😈
jam3scampbell/llama-lying
Code for our paper "Localizing Lying in Llama"
jam3scampbell/ARENA_2.0
Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.
jam3scampbell/cornell-ml-kaggle-winner
My winning submission (1st out of 155 participants) to Cornell's ML Kaggle competition
jam3scampbell/brain-representations
jam3scampbell/character-sim-interp
jam3scampbell/iti_capstone
Analyzing truth representations in LLMs across different kinds of truth and intervening on their hidden states to make LLMs more truthful
jam3scampbell/jamescampbell57.github.io
jam3scampbell/NLP-brain-biased-robustness
CS 6740 term project: "CereBERTo: Improving Distributional Robustness with Brain-Like Language Representations"
jam3scampbell/representation-engineering
Representation Engineering: A Top-Down Approach to AI Transparency
jam3scampbell/nlp-robust-finetuning
jam3scampbell/regex_transformer
jam3scampbell/rlhf-truthfulness
jam3scampbell/TransformerLens
TransformerLens