montemac / activation_additionsLinks
Algebraic value editing in pretrained language models
☆65Updated last year
Alternatives and similar repositories for activation_additions
Users that are interested in activation_additions are comparing it to the libraries listed below
Sorting:
- ☆83Updated 9 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- General-purpose activation steering library☆74Updated 3 weeks ago
- Steering Llama 2 with Contrastive Activation Addition☆154Updated last year
- ☆34Updated 2 weeks ago
- A Mechanistic Understanding of Alignment Algorithms: A Case Study on DPO and Toxicity.☆72Updated 2 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- Sparse probing paper full code.☆56Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆55Updated 7 months ago
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆34Updated last year
- Function Vectors in Large Language Models (ICLR 2024)☆167Updated last month
- 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
- Röttger et al. (NAACL 2024): "XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models"☆97Updated 3 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆47Updated 7 months ago
- ☆116Updated 9 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆101Updated 3 months ago
- ☆97Updated last month
- ☆120Updated 6 months ago
- Repo accompanying our paper "Do Llamas Work in English? On the Latent Language of Multilingual Transformers".☆76Updated last year
- ☆94Updated last year
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆89Updated last week
- [NAACL'25 Oral] Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering☆58Updated 6 months ago
- ☆44Updated last year
- ☆170Updated last month
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- For OpenMOSS Mechanistic Interpretability Team's Sparse Autoencoder (SAE) research.☆116Updated this week
- Code to enable layer-level steering in LLMs using sparse auto encoders☆17Updated 3 weeks ago
- Sparse Autoencoder Training Library☆50Updated last month
- Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization☆25Updated 10 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated last year