Code to enable layer-level steering in LLMs using sparse auto encoders
☆34Sep 18, 2025Updated 9 months ago
Alternatives and similar repositories for sae-steering
Users that are interested in sae-steering are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆28Nov 20, 2024Updated last year
- Materials for "Multi-property Steering of Large Language Models with Dynamic Activation Composition"☆14Nov 22, 2024Updated last year
- Experiments with representation engineering☆14Feb 28, 2024Updated 2 years ago
- A TinyStories LM with SAEs and transcoders☆14Apr 3, 2025Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆47May 31, 2024Updated 2 years ago
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆20Jan 19, 2025Updated last year
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆20Oct 11, 2024Updated last year
- The offical code for paper "What Constitutes a Faithful Summary? Preserving Author Perspectives in News Summarization"☆10Jun 23, 2024Updated 2 years ago
- Archive of questions from the Cambridge Mathematics Tripos☆10Jun 6, 2022Updated 4 years ago
- A framework for implementing equivariant DL☆10May 25, 2021Updated 5 years ago
- ☆36Jun 13, 2025Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆16Oct 21, 2025Updated 8 months ago
- ☆11Aug 24, 2022Updated 3 years ago
- 𝔸𝕄𝔹ℝ𝕆𝕊𝕀𝔸: A Benchmark for Parsing Ambiguous Questions into Database Queries☆16Oct 31, 2024Updated last year
- 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.
- A curated list of resources for activation engineering☆141Oct 2, 2025Updated 8 months ago
- FeatureAlignment = Alignment + Mechanistic Interpretability☆35Mar 8, 2025Updated last year
- ☆10Nov 28, 2023Updated 2 years ago
- ☆14May 8, 2023Updated 3 years ago
- Official codebase for "Analyzing the Generalization and Reliability of Steering Vectors"☆22Dec 14, 2024Updated last year
- A library for efficient patching and automatic circuit discovery.☆97Dec 31, 2025Updated 6 months ago
- Code release for the paper "Style Vectors for Steering Generative Large Language Models", accepted to the Findings of the EACL 2024.☆36Sep 26, 2024Updated last year
- Code for our paper "Decomposing The Dark Matter of Sparse Autoencoders"☆23Feb 6, 2025Updated last year
- Code Release for the 2023 NeurIPS Paper How does GPT-2 compute greater-than?: Interpreting mathematical abilities in a pre-trained langua…☆17Dec 6, 2024Updated 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.
- Exploring the Limitations of Large Language Models on Multi-Hop Queries☆33Mar 2, 2025Updated last year
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆69Aug 15, 2025Updated 10 months ago
- Sparse Autoencoder Training Library☆57May 1, 2025Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆103Sep 21, 2023Updated 2 years ago
- helper functions for processing and integrating visual language information with Qwen-VL Series Model☆17Aug 30, 2024Updated last year
- ☆21Apr 3, 2026Updated 2 months ago
- ☆16Oct 23, 2023Updated 2 years ago
- Click this --> https://zsdonghao.github.io☆10Jun 25, 2026Updated last week
- Pytorch implementation on OpenAI's Procgen ppo-baseline, built from scratch.☆14May 17, 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.
- Algebraic value editing in pretrained language models☆70Nov 1, 2023Updated 2 years ago
- The 4th rank system of the SemEval 2021 Task4.☆11May 7, 2022Updated 4 years ago
- Code for the paper ``Mapping Between fMRI Responses to Movies and their Natural Language Annotations'', submitted to NeuroImage.☆11Jun 1, 2017Updated 9 years ago
- ☆14Jun 17, 2026Updated 2 weeks ago
- (Model-written) LLM evals library☆19Dec 13, 2024Updated last year
- ICLR 2024: Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretations☆23May 1, 2025Updated last year
- experiment☆12Jan 1, 2023Updated 3 years ago