tilde-research / sieveLinks
Applying SAEs for fine-grained control
☆18Updated 5 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☆55Updated 7 months ago
- Modified to support crosscoder training.☆17Updated last week
- ☆43Updated 6 months ago
- ☆28Updated last year
- A small package implementing some useful wrapping around nnsight☆13Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- Sparse Autoencoder Training Library☆50Updated last month
- Engine for collecting, uploading, and downloading model activations☆18Updated 2 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- ☆50Updated 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 …☆180Updated this week
- ☆131Updated 2 months ago
- Open source interpretability artefacts for R1.☆140Updated last month
- Universal Neurons in GPT2 Language Models☆29Updated last year
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆16Updated 7 months ago
- ☆31Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year
- ☆121Updated last year
- ☆97Updated last month
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆200Updated 5 months ago
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆126Updated 3 weeks ago
- Attribution-based Parameter Decomposition☆23Updated this week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆89Updated last week
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆23Updated 3 months ago
- ☆23Updated 4 months ago
- ☆170Updated last month
- PyTorch library for Active Fine-Tuning☆77Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆75Updated 6 months ago
- ☆120Updated 6 months ago