science-of-finetuning / dictionary_learningLinks
Modified to support crosscoder training.
☆17Updated this week
Alternatives and similar repositories for dictionary_learning
Users that are interested in dictionary_learning are comparing it to the libraries listed below
Sorting:
- Applying SAEs for fine-grained control☆18Updated 5 months ago
- ☆43Updated 6 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- ☆97Updated last month
- ☆12Updated last month
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆181Updated this week
- ☆171Updated last month
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆124Updated 6 months ago
- ☆121Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆201Updated 5 months ago
- ☆223Updated 8 months ago
- ☆75Updated 3 months ago
- ☆94Updated 3 months ago
- ☆304Updated 2 weeks ago
- Attribution-based Parameter Decomposition☆24Updated this week
- A small package implementing some useful wrapping around nnsight☆13Updated this week
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆26Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- Sparse Autoencoder Training Library☆52Updated last month
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆28Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆22Updated 3 months ago
- ☆50Updated last month
- Mechanistic Interpretability Visualizations using React☆253Updated 5 months ago
- ☆31Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- ☆33Updated 4 months ago