Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"
☆23Feb 6, 2025Updated last year
Alternatives and similar repositories for SAE-Dark-Matter
Users that are interested in SAE-Dark-Matter are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"☆33Mar 31, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 6 months ago
- Mamba support for transformer lens☆19Sep 17, 2024Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆84Nov 27, 2024Updated last year
- Implementation of the BatchTopK activation function for training sparse autoencoders (SAEs)☆64Jul 24, 2025Updated 8 months ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- The official repository of 'Unnatural Language Are Not Bugs but Features for LLMs'☆24May 20, 2025Updated 11 months ago
- ☆26Jun 22, 2025Updated 9 months ago
- DESSERT Effeciently Searches Sets of Embeddings via Retrieval Tables☆17Feb 21, 2024Updated 2 years ago
- Codebase for Obfuscated Activations Bypass LLM Latent-Space Defenses☆30Feb 11, 2025Updated last year
- ☆35Feb 20, 2025Updated last year
- ☆28Nov 28, 2024Updated last year
- A fast high dimensional near neighbor search algorithm based on group testing and locality sensitive hashing☆23Dec 9, 2023Updated 2 years ago
- Code for our paper "Localizing Lying in Llama"☆14Apr 24, 2025Updated 11 months ago
- Unsupervised Grammar Induction with Combinatory Categorial Grammars☆10Jan 28, 2021Updated 5 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- This is the code repository for "Uncovering Safety Risks of Large Language Models through Concept Activation Vector"☆47Oct 13, 2025Updated 6 months ago
- ☆37Apr 30, 2024Updated last year
- A python sdk for LLM finetuning and inference on runpod infrastructure☆25Updated this week
- KV cache compression via sparse coding☆17Oct 26, 2025Updated 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 …☆250Apr 13, 2026Updated last week
- Sparsify transformers with SAEs and transcoders☆705Apr 6, 2026Updated 2 weeks ago
- TDMS 2.0 support for F# and C#☆13Dec 26, 2022Updated 3 years ago
- Code for the paper "Large Language Models Share Representations of Latent Grammatical Concepts Across Typologically Diverse Languages" (N…☆17Apr 13, 2025Updated last year
- ☆159Dec 30, 2025Updated 3 months 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.
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆254Feb 27, 2026Updated last month
- Code for the arXiv preprint "Answer, Assemble, Ace: Understanding How Transformers Answer Multiple Choice Questions"☆15Aug 2, 2025Updated 8 months ago
- A benchmark for mechanistic discovery of circuits in Transformers☆16Dec 15, 2024Updated last year
- ☆141Aug 4, 2024Updated last year
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- ☆409Aug 21, 2025Updated 8 months ago
- A CLI tool that helps AI researchers share datasets responsibly.☆22Sep 15, 2025Updated 7 months ago
- 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
- ☆12Apr 19, 2022Updated 4 years ago
- Serverless GPU API endpoints on Runpod - Get Bonus Credits • AdSkip the infrastructure headaches. Auto-scaling, pay-as-you-go, no-ops approach lets you focus on innovating your application.
- ASCETIC (Agony-baSed Cancer EvoluTion InferenCe) is a novel framework for the inference of a set of statistically significant temporal pa…☆12Apr 18, 2025Updated last year
- This is the implementation of CounterCurate, the data curation pipeline of both physical and semantic counterfactual image-caption pairs.☆19Jun 27, 2024Updated last year
- Code for the "Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning" paper.☆17Nov 21, 2025Updated 4 months ago
- ☆15Oct 21, 2023Updated 2 years ago
- Attribution-based Parameter Decomposition☆34Jun 11, 2025Updated 10 months ago
- Universal Neurons in GPT2 Language Models☆30May 28, 2024Updated last year
- Code to enable layer-level steering in LLMs using sparse auto encoders☆31Sep 18, 2025Updated 7 months ago