IBM / sae-steering
Code to enable layer-level steering in LLMs using sparse auto encoders
☆17Updated last week
Alternatives and similar repositories for sae-steering
Users that are interested in sae-steering are comparing it to the libraries listed below
Sorting:
- Algebraic value editing in pretrained language models☆65Updated last year
- General-purpose activation steering library☆68Updated last week
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆79Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆19Updated 5 months ago
- ☆82Updated 9 months ago
- ☆33Updated 2 weeks ago
- A library for efficient patching and automatic circuit discovery.☆64Updated 3 weeks ago
- PaCE: Parsimonious Concept Engineering for Large Language Models (NeurIPS 2024)☆35Updated 6 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆74Updated 5 months ago
- ☆14Updated last year
- ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"☆35Updated 3 months ago
- [ICLR 2025] Official Repository for "Tamper-Resistant Safeguards for Open-Weight LLMs"☆55Updated 2 months ago
- Sparse Autoencoder Training Library☆49Updated 2 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆151Updated 11 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆92Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 6 months ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆56Updated 2 months ago
- ☆25Updated 2 months ago
- ☆41Updated 6 months ago
- Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"☆105Updated 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…☆11Updated 3 months ago
- LoFiT: Localized Fine-tuning on LLM Representations☆38Updated 4 months ago
- ☆38Updated 2 weeks ago
- ☆31Updated 2 months ago
- This repository contains the code and data for the paper "SelfIE: Self-Interpretation of Large Language Model Embeddings" by Haozhe Chen,…☆48Updated 5 months ago
- ☆43Updated last year
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆25Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆100Updated 2 months ago
- ☆37Updated last year