hijohnnylin

neuronpedia.org

Pinned Repositories

automated-interpretability
Language:Python8 0 04
axbench
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
Language:Python00
ForumMagnum
The development repository for LessWrong2 and the EA Forum, based on Vulcan JS
Language:TypeScript0 0 00
mats_sae_training
Training Sparse Autoencoders on Language Models
Language:HTML4 0 01
neuronpedia-docs
Language:TypeScript0 1 00
neuronpedia-python
Python Library for Neuronpedia API
Language:Python3 1 02
neuronpedia-scorer
Language:Python16 2 01
sae-auto-interp
Language:Jupyter Notebook00
sae_vis
Language:HTML1 0 00
sparse_autoencoder
Clone of OAI Sparse Autoencoder, specifically to remove version requirements
Language:Python0 0 00

hijohnnylin's Repositories

hijohnnylin/neuronpedia-scorer
Language:Python16 2 01
hijohnnylin/automated-interpretability
Language:Python8 0 04
hijohnnylin/mats_sae_training
Training Sparse Autoencoders on Language Models
Language:HTML4 0 01
hijohnnylin/neuronpedia-python
Python Library for Neuronpedia API
Language:Python3 1 02
hijohnnylin/sae_vis
Language:HTML1 0 00
hijohnnylin/axbench
Stanford NLP Python library for benchmarking the utility of LLM interpretability methods
Language:Python00
hijohnnylin/ForumMagnum
The development repository for LessWrong2 and the EA Forum, based on Vulcan JS
Language:TypeScript0 0 00
hijohnnylin/neuronpedia-docs
Language:TypeScript0 1 00
hijohnnylin/sae-auto-interp
Language:Jupyter Notebook00
hijohnnylin/sparse_autoencoder
Clone of OAI Sparse Autoencoder, specifically to remove version requirements
Language:Python0 0 00
hijohnnylin/transcoder_circuits
Language:Jupyter Notebook0 0 00
hijohnnylin/TransformerLens
A library for mechanistic interpretability of GPT-style language models