tilde-research / sieveLinks
Applying SAEs for fine-grained control
☆18Updated 6 months ago
Alternatives and similar repositories for sieve
Users that are interested in sieve are comparing it to the libraries listed below
Sorting:
- ☆44Updated 7 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Modified to support crosscoder training.☆17Updated this week
- A small package implementing some useful wrapping around nnsight☆13Updated 3 weeks ago
- ☆28Updated last year
- ☆57Updated 2 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 7 months ago
- ☆134Updated 2 months ago
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Attribution-based Parameter Decomposition☆25Updated 2 weeks ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆108Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆67Updated 2 months ago
- ☆101Updated 3 weeks ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆185Updated this week
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆31Updated last year
- ☆13Updated 2 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆202Updated 6 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆18Updated 8 months ago
- ☆27Updated 4 months ago
- ☆121Updated last year
- ☆29Updated 10 months ago
- ☆173Updated 2 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆35Updated last year
- ☆131Updated 7 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆134Updated this week
- ☆84Updated 2 months ago
- Universal Neurons in GPT2 Language Models☆29Updated last year
- Open source interpretability artefacts for R1.☆149Updated 2 months ago