JoshEngels / SAE-ProbesLinks
Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"
☆27Updated 5 months ago
Alternatives and similar repositories for SAE-Probes
Users that are interested in SAE-Probes are comparing it to the libraries listed below
Sorting:
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆90Updated 9 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆77Updated 9 months ago
- The repository contains code for Adaptive Data Optimization☆25Updated 8 months ago
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆44Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- ☆72Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆124Updated 2 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆78Updated last year
- NeurIPS 2024 tutorial on LLM Inference☆47Updated 8 months ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆59Updated 2 weeks ago
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆46Updated 9 months ago
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆48Updated last year
- ☆100Updated last year
- ☆28Updated 6 months ago
- ☆15Updated last year
- Language models scale reliably with over-training and on downstream tasks☆98Updated last year
- Replicating O1 inference-time scaling laws☆89Updated 9 months ago
- Code for the paper "Fishing for Magikarp"☆163Updated 3 months ago
- ☆90Updated last year
- ☆50Updated last year
- ☆35Updated last year
- Exploration of automated dataset selection approaches at large scales.☆47Updated 5 months ago
- 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
- ☆23Updated 7 months ago
- Code repo for the model organisms and convergent directions of EM papers.☆26Updated last month
- PASTA: Post-hoc Attention Steering for LLMs☆122Updated 9 months ago
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆24Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆177Updated 4 months ago
- ☆31Updated last year
- CodeUltraFeedback: aligning large language models to coding preferences (TOSEM 2025)☆72Updated last year