ckkissane

ckkissane's Stars

• openai/transformer-debugger

  Language:Python4.1k2514241

• gpu-mode/lectures

  Material for gpu-mode lectures

  Language:Jupyter Notebook3.3k489338

• TransformerLensOrg/TransformerLens

  A library for mechanistic interpretability of GPT-style language models

  Language:Python1.7k16266314

• jacobhilton/deep_learning_curriculum

  Language model alignment-focused deep learning curriculum

  1.3k171110

• jbloomAus/SAELens

  Training Sparse Autoencoders on Language Models

  Language:Jupyter Notebook5457120132

• EleutherAI/sae

  Sparse autoencoders

  Language:Python39071451

• openai/sparse_autoencoder

  Language:Python389111439

• callummcdougall/ARENA_3.0

  Language:HTML387819236

• imbue-ai/cluster-health

  Language:Python28314838

• TransformerLensOrg/CircuitsVis

  Mechanistic Interpretability Visualizations using React

  Language:Jupyter Notebook21222631

• callummcdougall/ARENA_2.0

  Resources for skilling up in AI alignment research engineering. Covers basics of deep learning, mechanistic interpretability, and RL.

  Language:HTML2065580

• ai-safety-foundation/sparse_autoencoder

  Sparse Autoencoder for Mechanistic Interpretability

  Language:Python20044140

• HoagyC/sparse_coding

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

  Language:Jupyter Notebook1982428

• anthropics/PySvelte

  A library for bridging Python and HTML/Javascript (via Svelte) for creating interactive visualizations

  Language:Python17638035

• callummcdougall/sae_vis

  Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).

  Language:HTML17372137

• likenneth/othello_world

  Emergent world representations: Exploring a sequence model trained on a synthetic task

  Language:Jupyter Notebook1725440

• saprmarks/dictionary_learning

  Language:Python1675741

• andyrdt/refusal_direction

  Code and results accompanying the paper "Refusal in Language Models Is Mediated by a Single Direction".

  Language:Python1394628

• saprmarks/feature-circuits

  Language:Python1194524

• nrimsky/LM-exp

  LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces

  Language:Jupyter Notebook821023

• wesg52/sparse-probing-paper

  Sparse probing paper full code.

  Language:Jupyter Notebook522210

• EleutherAI/aria

  Language:Python424011

• wesg52/universal-neurons

  Universal Neurons in GPT2 Language Models

  Language:Jupyter Notebook27326

• callummcdougall/sae_visualizer

  Language:HTML24411

• jbloomAus/SAEDashboard

  Language:Python24443

• callummcdougall/TransformerLens-intro

  Language:HTML11201

• callummcdougall/path_patching

  Implementation of path patching & activation patching (will eventually add to TransformerLens).

  Language:Python10212

• neelnanda-io/Neuroscope

  Accompanying codebase for neuroscope.io, a website for displaying max activating dataset examples for language model neurons

  Language:Python9105

• callummcdougall/CircuitsVis

  Mechanistic Interpretability Visualizations using React

  Language:Jupyter Notebook32

• neelnanda-io/Tiny-Stories-SAEs

  Language:Python3100