Pinned Repositories
alphabetical_probe
Experimental code which trains 26 linear probes to detect the presence of alphabetic letters in GPT-J token strings, given their embeddings. Exploring the resulting vector arithmetic and its impact on GPT-J spelling abilities
arena-v1
arena-v1-ldn
ARENA_2.0
I'm teaching ARENA 2.0 and providing students with direction on careers and personal development.
DecisionTransformerInterpretability
Interpreting how transformers simulate agents performing RL tasks
SAEDashboard
SAELens
Training Sparse Autoencoders on Language Models
toy_model_interpretability
I'd like to start playing around with toy models to better understand results in recent papers.
TransformerLens
TransformerLens
A library for mechanistic interpretability of GPT-style language models
jbloomAus's Repositories
jbloomAus/SAELens
Training Sparse Autoencoders on Language Models
jbloomAus/DecisionTransformerInterpretability
Interpreting how transformers simulate agents performing RL tasks
jbloomAus/SAEDashboard
jbloomAus/alphabetical_probe
Experimental code which trains 26 linear probes to detect the presence of alphabetic letters in GPT-J token strings, given their embeddings. Exploring the resulting vector arithmetic and its impact on GPT-J spelling abilities
jbloomAus/toy_model_interpretability
I'd like to start playing around with toy models to better understand results in recent papers.
jbloomAus/TransformerLens
jbloomAus/arena-v1
jbloomAus/arena-v1-ldn
jbloomAus/ARENA_2.0
I'm teaching ARENA 2.0 and providing students with direction on careers and personal development.
jbloomAus/ARENA_2.0-RLHF
Preparing content for the ARENA RLHF day.
jbloomAus/SparseAutoencoderSuperposition
jbloomAus/babyai
BabyAI platform. A testbed for training agents to understand and execute language commands.
jbloomAus/Backwards
jbloomAus/Exploring-2L-SAE
jbloomAus/geom_median
Fast and differentiable geometric median, a multivariate median analogue. Install with `pip install geom-median`
jbloomAus/Minigrid
Simple and easily configurable grid world environments for reinforcement learning
jbloomAus/Module-1
Module 1 - Autodifferentiation
jbloomAus/post--memory-dt-features
jbloomAus/protein-inference
A python package for protein inference in Mass Spectrometric data analysis.
jbloomAus/rust_cli_project
I'm teaching myself Rust.
jbloomAus/rust_text_editor
Learning by doing with Rust. Following along the Hecto tutorial https://www.philippflenker.com/hecto/
jbloomAus/sparse_autoencoder
Sparse Autoencoder for Mechanistic Interpretability
jbloomAus/SpellingSAEExperiment