hoagyc Goto Github PK

arc

Work on the Abstraction and Reasoning Challenge at Kaggle

autointerpret

Attempt to interpret neurons automatically using GPT-4. Now obsolete due to openai/automated-interpretability

autosnake

bayes_calc

compress_check

cpython

The Python programming language

crime-regression

dd_replication

distrib_feats

Code for "Distributed Features and Non-linearities" post.

dotfiles

borrowed from @McHughes288

easy-sae-training

Easy training for Sparse Linear Autoencoders (https://arxiv.org/abs/2309.08600) with data from TransformerLens models.

econsim

efficientzero

Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.

examples

A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.

gaussian-processes

hidden_paper

hiddeninfo

Experiments for creating interpretable latent spaces by screening off hidden info.

hoagyc.github.io

launcher

muz

Attempting to replicate EfficientZero

natural-abstraction

pytextb

sparse_autoencoder

Sparse Autoencoder for Mechanistic Interpretability

sparse_coding

Using sparse coding to find distributed representations used by neural networks.

steering_directions

tensorflow

testing-confounders

tm_search

tokenback

transformers_toy_compute_model