Multi-Layer Sparse Autoencoders (ICLR 2025)
☆29Feb 6, 2026Updated 3 weeks ago
Alternatives and similar repositories for mlsae
Users that are interested in mlsae are comparing it to the libraries listed below
Sorting:
- ☆32Feb 15, 2026Updated 2 weeks ago
- ☆15Aug 19, 2025Updated 6 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆34Mar 8, 2025Updated 11 months ago
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- ☆17Feb 25, 2026Updated last week
- ☆20Apr 10, 2025Updated 10 months ago
- Applying SAEs for fine-grained control☆25Dec 15, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆64Oct 27, 2024Updated last year
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆10Dec 30, 2024Updated last year
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆12Oct 31, 2024Updated last year
- ☆15Mar 13, 2025Updated 11 months ago
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆75Jun 23, 2025Updated 8 months ago
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆16Nov 21, 2025Updated 3 months ago
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆195Updated this week
- ☆571Jul 19, 2024Updated last year
- 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 p…☆13Jan 26, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Oct 21, 2025Updated 4 months ago
- Tools for optimizing steering vectors in LLMs.☆20Apr 10, 2025Updated 10 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- ☆153Dec 30, 2025Updated 2 months ago
- KernelBench v2: Can LLMs Write GPU Kernels? - Benchmark with Torch -> Triton (and more!) problems☆21Jul 4, 2025Updated 8 months ago
- ☆209Oct 14, 2025Updated 4 months ago
- Codes for the paper The emergence of clusters in self-attention dynamics.☆17Dec 18, 2023Updated 2 years ago
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated last year
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated last year
- ☆33Jul 9, 2025Updated 7 months ago
- ☆23Jun 30, 2025Updated 8 months ago
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 2025Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆247Updated this week
- Code for experiments on transformers using Markovian data.☆22Nov 22, 2024Updated last year
- A library for mechanistic anomaly detection☆22Jan 9, 2025Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- ☆27Nov 28, 2024Updated last year
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 5 months ago
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆30Jan 10, 2026Updated last month
- Codebase for "On Targeted Manipulation and Deception when Optimizing LLMs for User Feedback". This repo implements a generative multi-tur…☆23Dec 3, 2024Updated last year
- ☆23Jan 7, 2025Updated last year