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. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆58Oct 30, 2025Updated 6 months ago
- Code for the paper: Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discovery. ECCV 2024.☆58Nov 3, 2024Updated last year
- ☆162May 1, 2026Updated last week
- A benchmark for mechanistic discovery of circuits in Transformers☆17Dec 15, 2024Updated last year
- ☆30Aug 2, 2024Updated last year
- GPUs on demand by Runpod - Special Offer Available • AdRun AI, ML, and HPC workloads on powerful cloud GPUs—without limits or wasted spend. Deploy GPUs in under a minute and pay by the second.
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- Applying SAEs for fine-grained control☆26Dec 15, 2024Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆35Sep 13, 2023Updated 2 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆30May 23, 2024Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆149Feb 21, 2025Updated last year
- Spurious Features Everywhere - Large-Scale Detection of Harmful Spurious Features in ImageNet☆32Aug 22, 2023Updated 2 years ago
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 10 months ago
- ☆17Feb 14, 2024Updated 2 years ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [NeurIPS XAIA & Springer] Code and notebooks to paper "A Fresh Look at Sanity Checks for Saliency Maps"☆25Jul 12, 2024Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆27Nov 20, 2024Updated last year
- ☆28Nov 28, 2024Updated last year
- ☆20Feb 8, 2024Updated 2 years ago
- ☆41Sep 28, 2025Updated 7 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆30Feb 6, 2026Updated 3 months ago
- ViT Prisma is a mechanistic interpretability library for Vision and Video Transformers (ViTs).☆356Jul 23, 2025Updated 9 months ago
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated last year
- ☆17Jul 6, 2020Updated 5 years ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- Tools for running experiments on RL agents in procgen environments☆20Apr 5, 2024Updated 2 years ago
- ☆11Mar 24, 2025Updated last year
- ☆105Oct 30, 2023Updated 2 years ago
- ☆16May 1, 2025Updated last year
- [ICLR 2025] General-purpose activation steering library☆167Sep 18, 2025Updated 7 months ago
- ☆13Aug 19, 2024Updated last year
- Can LLMs Predict Their Own Failures? Self-Awareness via Internal Circuits☆41Jan 8, 2026Updated 4 months ago
- This is the official code for the paper "Lazy Safety Alignment for Large Language Models against Harmful Fine-tuning" (NeurIPS2024)☆27Sep 10, 2024Updated last year
- ☆14Feb 26, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆24Dec 11, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆97Dec 31, 2025Updated 4 months ago
- ☆10Aug 25, 2020Updated 5 years ago
- ☆281Oct 1, 2024Updated last year
- A vanilla implementation of ReAct: Synergizing Reasoning and Acting in Language Models☆17Mar 26, 2025Updated last year
- ☆16Jun 4, 2025Updated 11 months ago
- [NeurIPS 2025@FoRLM] R1-Compress: Long Chain-of-Thought Compression via Chunk Compression and Search☆17Jan 24, 2026Updated 3 months ago