MaheepChaudhary / SAE-RavelView external linksLinks
Providing the answer to "How to do patching on all available SAEs on GPT-2?". It is an official repository of the implementation of the paper "Evaluating Open-Source Sparse Autoencoders on Disentangling Factual Knowledge in GPT-2 Small"
☆13Jan 26, 2025Updated last year
Alternatives and similar repositories for SAE-Ravel
Users that are interested in SAE-Ravel are comparing it to the libraries listed below
Sorting:
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆57Oct 30, 2025Updated 3 months ago
- ☆146Dec 30, 2025Updated last month
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆17Feb 14, 2024Updated 2 years ago
- ☆25Nov 28, 2024Updated last year
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- ☆17Jul 6, 2020Updated 5 years ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆57Nov 3, 2024Updated last year
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- ☆24Aug 23, 2025Updated 5 months ago
- ☆104Oct 30, 2023Updated 2 years ago
- ☆30Aug 2, 2024Updated last year
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆25Sep 10, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28May 23, 2024Updated last year
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆29Feb 6, 2026Updated last week
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Aug 22, 2023Updated 2 years ago
- Attribution-based Parameter Decomposition☆33Jun 11, 2025Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆90Dec 31, 2025Updated last month
- Steering vectors for transformer language models in Pytorch / Huggingface☆140Feb 21, 2025Updated 11 months ago
- ☆35Sep 13, 2023Updated 2 years ago
- Collection of Reverse Engineering in Large Model☆36Jan 8, 2025Updated last year
- Code for the paper "Distinguishing the Knowable from the Unknowable with Language Models"☆11Apr 15, 2024Updated last year
- [EMNLP 2020] Collective HumAn OpinionS on Natural Language Inference Data☆40Apr 7, 2022Updated 3 years ago
- [NeurIPS 2023 D&B Track] Code and data for paper "Revisiting Out-of-distribution Robustness in NLP: Benchmarks, Analysis, and LLMs Evalua…☆36Jun 8, 2023Updated 2 years ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆177Feb 9, 2026Updated last week
- ☆51Oct 23, 2023Updated 2 years ago
- ☆39Jun 19, 2021Updated 4 years ago
- ☆394Aug 21, 2025Updated 5 months ago
- Test-Time Label-Shift Adaptation☆13May 24, 2023Updated 2 years ago
- Identification of the Adversary from a Single Adversarial Example (ICML 2023)☆10Jul 15, 2024Updated last year
- ☆267Oct 1, 2024Updated last year
- ☆47Sep 29, 2024Updated last year
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆60Jul 24, 2025Updated 6 months ago
- ☆44Oct 1, 2024Updated last year
- The repository contains lists of papers on causality and how relevant techniques are being used to further enhance deep learning era comp…☆100Aug 28, 2023Updated 2 years ago
- ☆10Oct 20, 2023Updated 2 years ago