Pinned Repositories
aboutme
Config files for my GitHub profile.
AC-Solver
A long-horizon, sparse-reward math environment for reinforcement learning. Official code repo for "What makes Math problems hard for reinforcement learning: A case study".
attn_saes
feature-interface
sae_vis
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
SAELens
Training Sparse Autoencoders on Language Models
scaling_laws
An open-source implementation of Scaling Laws for Neural Language Models using nanoGPT
shehper.github.io
sparse-dictionary-learning
An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"
transformer-debugger
shehper's Repositories
shehper/sparse-dictionary-learning
An Open Source Implementation of Anthropic's Paper: "Towards Monosemanticity: Decomposing Language Models with Dictionary Learning"
shehper/scaling_laws
An open-source implementation of Scaling Laws for Neural Language Models using nanoGPT
shehper/AC-Solver
A long-horizon, sparse-reward math environment for reinforcement learning. Official code repo for "What makes Math problems hard for reinforcement learning: A case study".
shehper/attn_saes
shehper/aboutme
Config files for my GitHub profile.
shehper/feature-interface
shehper/sae_vis
Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).
shehper/SAELens
Training Sparse Autoencoders on Language Models
shehper/shehper.github.io
shehper/transformer-debugger