IBM / sae-steeringLinks
Code to enable layer-level steering in LLMs using sparse auto encoders
☆26Updated 4 months ago
Alternatives and similar repositories for sae-steering
Users that are interested in sae-steering are comparing it to the libraries listed below
Sorting:
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆128Updated 2 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆118Updated last year
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆91Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆78Updated 9 months ago
- Sparse Autoencoder Training Library☆54Updated 4 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 10 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 10 months ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆60Updated last month
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆39Updated 10 months ago
- A library for efficient patching and automatic circuit discovery.☆76Updated 2 months ago
- ☆31Updated 7 months ago
- [EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated last month
- [ICLR 2025] General-purpose activation steering library☆102Updated 3 weeks ago
- ☆72Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆124Updated 7 months ago
- Steering Llama 2 with Contrastive Activation Addition☆180Updated last year
- [COLING'25] Exploring Concept Depth: How Large Language Models Acquire Knowledge at Different Layers?☆80Updated 7 months ago
- [NeurIPS 2024] Knowledge Circuits in Pretrained Transformers☆157Updated 7 months ago
- ☆78Updated 8 months ago
- [NeurIPS 2024] Goldfish Loss: Mitigating Memorization in Generative LLMs☆92Updated 10 months ago
- NeurIPS'24 - LLM Safety Landscape☆29Updated 6 months ago
- Function Vectors in Large Language Models (ICLR 2024)☆179Updated 5 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- ☆190Updated 5 months ago
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆51Updated 9 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆211Updated last week
- ☆168Updated 10 months ago