bartbussmann / matryoshka_saeLinks
☆40Updated 7 months ago
Alternatives and similar repositories for matryoshka_sae
Users that are interested in matryoshka_sae are comparing it to the libraries listed below
Sorting:
- ☆114Updated last month
- ☆184Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆207Updated this week
- ☆104Updated 6 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆24Updated 6 months ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆53Updated 10 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆40Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- PyTorch library for Active Fine-Tuning☆89Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- ☆67Updated 2 weeks ago
- ☆53Updated 9 months ago
- ☆17Updated this week
- ☆21Updated 9 months ago
- Sparse Autoencoder for Mechanistic Interpretability☆260Updated last year
- ☆79Updated 5 months ago
- ☆90Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆27Updated last year
- Modified to support crosscoder training.☆22Updated last month
- Steering Llama 2 with Contrastive Activation Addition☆176Updated last year
- ☆15Updated last year
- Using sparse coding to find distributed representations used by neural networks.☆264Updated last year
- ☆163Updated 9 months ago
- ☆52Updated 4 months ago
- ☆122Updated last year