tilde-research / sieveLinks
Applying SAEs for fine-grained control
☆23Updated 8 months ago
Alternatives and similar repositories for sieve
Users that are interested in sieve are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆58Updated 10 months ago
- ☆67Updated 2 weeks ago
- Sparse Autoencoder Training Library☆54Updated 3 months ago
- ☆32Updated last year
- ☆139Updated last week
- 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
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆212Updated 8 months ago
- ☆53Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆114Updated last month
- Engine for collecting, uploading, and downloading model activations☆22Updated 4 months ago
- ☆29Updated last year
- ☆23Updated 6 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆191Updated last year
- ☆126Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆122Updated 6 months ago
- Modified to support crosscoder training.☆22Updated 3 weeks ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- A tiny easily hackable implementation of a feature dashboard.☆12Updated last month
- A toolkit for describing model features and intervening on those features to steer behavior.☆198Updated 9 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 9 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆24Updated 6 months ago
- Open source interpretability artefacts for R1.☆158Updated 4 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆153Updated 2 months ago
- Attribution-based Parameter Decomposition☆28Updated 2 months ago
- ☆184Updated last month
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Mechanistic Interpretability Visualizations using React☆281Updated 8 months ago