kxcloud / gradient-routingLinks
☆9Updated 6 months ago
Alternatives and similar repositories for gradient-routing
Users that are interested in gradient-routing are comparing it to the libraries listed below
Sorting:
- A TinyStories LM with SAEs and transcoders☆11Updated 2 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆21Updated 7 months ago
- MishformerLens intends to be a drop-in replacement for TransformerLens that AST patches HuggingFace Transformers rather than implementing…☆10Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- A small package implementing some useful wrapping around nnsight☆13Updated this week
- ☆85Updated 10 months ago
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 8 months ago
- ☆29Updated 10 months ago
- Code to enable layer-level steering in LLMs using sparse auto encoders☆19Updated last month
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆18Updated 8 months ago
- ☆37Updated last month
- ☆26Updated 2 years ago
- ☆57Updated last week
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- Experiments with representation engineering☆11Updated last year
- ☆99Updated 4 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 8 months ago
- ☆44Updated 7 months ago
- ☆34Updated 5 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 5 months ago
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆42Updated last month
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆70Updated last year
- ☆227Updated 8 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- ☆95Updated 4 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 8 months ago
- ☆121Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆22Updated 4 months ago
- ☆18Updated last year