Code to reproduce key results for "Interpreting Attention Layer Outputs with Sparse Autoencoders"
☆11Jul 27, 2024Updated 2 years ago
Alternatives and similar repositories for attention-output-saes
Users that are interested in attention-output-saes 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 experiments on transformers using Markovian data.☆22Nov 22, 2024Updated last year
- [NeurIPS'25] Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders☆16May 28, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆18Oct 21, 2025Updated last year
- ☆12Feb 6, 2025Updated 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…☆14Jan 26, 2025Updated last year
- 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.
- 2021年春季南京大学 机器学习导论 课程作业☆10Jun 22, 2021Updated 5 years ago
- Lightweight, zero-dependency Vue 3 drag and drop library using native HTML5 Drag and Drop API☆12Sep 6, 2026Updated 2 months ago
- ☆40Oct 15, 2026Updated 3 weeks ago
- volumetric brush implementation, heavily inspired by toxiclibs☆14Dec 10, 2022Updated 3 years ago
- Multivariate Time Series Classification- Activity Recognition☆16Jun 5, 2020Updated 6 years ago
- ☆26Dec 20, 2023Updated 2 years ago
- A sparse autoencoder I trained on Mistral's open source 7b model!☆10Aug 7, 2024Updated 2 years ago
- ☆18Jan 16, 2025Updated last year
- ☆10Jul 27, 2026Updated 3 months 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.
- ☆14Jul 13, 2025Updated last year
- Decoder only transformer, built from scratch with PyTorch☆34Oct 22, 2023Updated 3 years ago
- Dynamical low rank training for neural networks☆11Aug 24, 2023Updated 3 years ago
- ☆12Sep 26, 2026Updated last month
- 支付宝推荐的公钥证书方式模式SDK、示例及相关工具☆11May 7, 2023Updated 3 years ago
- codes and plots for "Active-Dormant Attention Heads: Mechanistically Demystifying Extreme-Token Phenomena in LLMs"☆11Dec 30, 2024Updated last year
- ☆18Nov 22, 2022Updated 3 years ago
- ☆13Sep 27, 2022Updated 4 years ago
- ☆16May 24, 2026Updated 5 months ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- An repository of 2025-2026 AI Safety and Alignment programs, camps, and workshops.☆22May 18, 2025Updated last year
- Official Pytorch implementation of Chromatic Graph Transformers☆10Jun 14, 2023Updated 3 years ago
- Clustered Compositional Embeddings☆13Oct 25, 2023Updated 3 years ago
- WasmGuard: Enhancing Web Security through Robust Raw-Binary Detection of WebAssembly Malware☆11May 19, 2025Updated last year
- [ICLR'26] Beyond Linear Probes: Dynamic Safety Monitoring for Language Models☆13Oct 1, 2025Updated last year
- Fast, Numerically Stable, and Auto-Differentiable Spectral Clipping via Newton-Schulz Iteration☆12Jun 21, 2025Updated last year
- ☆13Apr 16, 2024Updated 2 years ago
- Transductive Active Learning with Application to Safe Bayesian Optimization☆11Mar 5, 2025Updated last year
- A self-hosted, secure code execution sandbox for LLM agents deployed on your cloud infrastructure using SkyPilot. Built on llm-sandbox fo…☆17Jul 20, 2025Updated last year
- 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.
- Custom::LexBot | AWS CloudFormation Custom Lambda Resource | Lex Bot☆10Jan 13, 2021Updated 5 years ago
- ☆22Apr 6, 2021Updated 5 years ago
- SAT Competition 2024☆11Updated this week
- A PyTorch exercise in implementing a continuous time LSTM to simulate Neural Hawkes Process based on the paper by Hongyuan Mei and Jason …☆11Apr 11, 2023Updated 3 years ago
- Least Squares Regression for subspace clustering☆11May 27, 2018Updated 8 years ago
- KDD-CUP -2015☆11May 9, 2020Updated 6 years ago
- ☆12Nov 24, 2025Updated 11 months ago
Are these results useful?