neelnanda-io

followers

following

stars

Google DeepMind

London

Neel Nanda's repositories

1L-Sparse-Autoencoder

Language:PythonMIT85 20

LLaMA-Chat-Finetuning-Circuits

Language:PythonMIT400

Stable-Diffusion-Interp

Language:PythonMIT4 10

Prediction-Suppression-Neurons

MIT300

Tiny-Stories-SAEs

Language:PythonMIT300

Exploring-2L-SAE

Language:PythonMIT200

GPT-Spelling-Bee

Language:PythonMIT200

Intro-to-MI-Techniques

MIT200

mats_sae_training

Training Sparse Autoencoders on Language Models

Language:HTMLMIT200

SAE-Feature-Splitting

Language:PythonMIT200

Act-Add

Language:PythonMIT100

neelutils

Random utils for personal use

Language:Python1 10

Refusal-Replication

Language:PythonMIT1 10

Testing-Gemma-2

MIT100

An-Neuron

Language:Python000

Coloured-Object-Subspaces

Language:PythonMIT000

Copy-Suppression-Exploration

Language:PythonMIT000

diffusers

🤗 Diffusers: State-of-the-art diffusion models for image and audio generation in PyTorch

Language:PythonApache-2.0000

Finding-An-SAE-Circuit

Language:PythonMIT000

Greater-Than

Language:PythonMIT000

LLaMA-Fact

Language:PythonMIT000

Memorisation-GPT2

MIT000

Multilingual-Representations

Language:PythonMIT000

neelnanda-io.github.io

Language:HTML000

Neuron-Families

Language:PythonMIT000

Object-Size-Comparison

Language:PythonMIT000

Qwen-MLP-Exploration

Language:PythonMIT000

S-Inhibition-Heads

Language:PythonMIT000

TLWebsiteRedirect

Language:HTML000

Variable-Binding

000