tilde-research / sieveLinks
Applying SAEs for fine-grained control
☆24Updated 9 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☆59Updated 11 months ago
- ☆142Updated last month
- ☆71Updated last month
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆193Updated last year
- The simplest, fastest repository for training/finetuning medium-sized GPTs.☆164Updated 3 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated last week
- Open source interpretability artefacts for R1.☆160Updated 5 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- ☆54Updated 10 months ago
- ☆36Updated 7 months ago
- ☆29Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆81Updated 10 months ago
- ☆35Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- Extract full next-token probabilities via language model APIs☆247Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Updated 3 weeks ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- Attribution-based Parameter Decomposition☆31Updated 3 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Understand and test language model architectures on synthetic tasks.☆229Updated 2 weeks ago
- ☆127Updated last year
- ☆103Updated this week
- nanoGPT-like codebase for LLM training☆107Updated 4 months ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆204Updated 11 months ago
- A MAD laboratory to improve AI architecture designs 🧪☆129Updated 9 months ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆230Updated 2 months ago
- Training-Ready RL Environments + Evals☆116Updated last week
- Official repo for Learning to Reason for Long-Form Story Generation☆72Updated 5 months ago