Multi-Layer Sparse Autoencoders (ICLR 2025)
☆29Feb 6, 2026Updated last month
Alternatives and similar repositories for mlsae
Users that are interested in mlsae are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- Trains Sparse Autoencoders based on outputs from language models☆11Oct 7, 2024Updated last year
- ☆33Feb 15, 2026Updated last month
- ☆18Mar 13, 2026Updated last week
- Applying SAEs for fine-grained control☆26Dec 15, 2024Updated last year
- DigitalOcean Gradient AI Platform • AdBuild production-ready AI agents using customizable tools or access multiple LLMs through a single endpoint. Create custom knowledge bases or connect external data.
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆10Dec 30, 2024Updated last year
- ☆20Apr 10, 2025Updated 11 months ago
- Localization of Knowledge in Text-to-Image Models☆12Oct 8, 2024Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Oct 27, 2024Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆16Nov 21, 2025Updated 4 months ago
- ☆578Jul 19, 2024Updated last year
- ☆211Oct 14, 2025Updated 5 months ago
- ☆33Jul 9, 2025Updated 8 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆30Oct 27, 2025Updated 4 months ago
- Managed Kubernetes at scale on DigitalOcean • AdDigitalOcean Kubernetes includes the control plane, bandwidth allowance, container registry, automatic updates, and more for free.
- Code for experiments on transformers using Markovian data.☆22Nov 22, 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
- [ICLR 2025] Monet: Mixture of Monosemantic Experts for Transformers☆76Jun 23, 2025Updated 9 months ago
- Performant framework for training, analyzing and visualizing Sparse Autoencoders (SAEs) and their frontier variants.☆206Updated this week
- PyTorch implementation of StableMask (ICML'24)☆15Jun 27, 2024Updated last year
- Codes for the paper The emergence of clusters in self-attention dynamics.☆17Dec 18, 2023Updated 2 years ago
- [ICML 2025] Official code of "AlphaDPO: Adaptive Reward Margin for Direct Preference Optimization"☆30Jan 10, 2026Updated 2 months ago
- ☆157Dec 30, 2025Updated 2 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆13Jul 18, 2024Updated last year
- NordVPN Special Discount Offer • AdSave on top-rated NordVPN 1 or 2-year plans with secure browsing, privacy protection, and support for for all major platforms.
- ☆24Aug 23, 2025Updated 7 months ago
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆251Feb 27, 2026Updated 3 weeks ago
- u-MPS implementation and experimentation code used in the paper Tensor Networks for Probabilistic Sequence Modeling (https://arxiv.org/ab…☆19Jul 2, 2020Updated 5 years ago
- ☆26Jan 14, 2025Updated last year
- KernelBench v2: Can LLMs Write GPU Kernels? - Benchmark with Torch -> Triton (and more!) problems☆22Jul 4, 2025Updated 8 months ago
- Official Code for What Makes and Breaks Safety Fine-tuning? A Mechanistic Study (NeurIPS 2024)☆12Oct 31, 2024Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆246Updated this week
- Our research proposes a novel MoGU framework that improves LLMs' safety while preserving their usability.☆18Jan 14, 2025Updated last year
- ☆28Nov 28, 2024Updated last year
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆36Feb 26, 2024Updated 2 years ago
- ☆15Mar 13, 2025Updated last year
- ☆25Feb 20, 2026Updated last month
- Code for safety test in "Keeping LLMs Aligned After Fine-tuning: The Crucial Role of Prompt Templates"☆22Sep 21, 2025Updated 6 months ago
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 5 months ago
- The loss landscape of Large Language Models resemble basin!☆36Jul 8, 2025Updated 8 months ago
- ☆23Jun 30, 2025Updated 8 months ago