mishajw / repengLinks
Experiments with representation engineering
☆11Updated last year
Alternatives and similar repositories for repeng
Users that are interested in repeng are comparing it to the libraries listed below
Sorting:
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆16Updated 7 months ago
- A library for efficient patching and automatic circuit discovery.☆65Updated last month
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆14Updated 7 months ago
- 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
- Sparse Autoencoder Training Library☆52Updated last month
- 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
- Sparse probing paper full code.☆56Updated last year
- Algebraic value editing in pretrained language models☆65Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆93Updated last year
- ☆28Updated last year
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 4 months ago
- NeuroSurgeon is a package that enables researchers to uncover and manipulate subnetworks within models in Huggingface Transformers☆41Updated 3 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆103Updated 3 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆76Updated last year
- General-purpose activation steering library☆75Updated 3 weeks ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆20Updated 6 months ago
- ☆83Updated 9 months ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆26Updated last year
- ☆31Updated last year
- ☆97Updated last month
- ☆22Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆155Updated last year
- ☆43Updated 6 months ago
- ☆121Updated last year
- ☆34Updated 2 weeks ago
- This is the official repository for the "Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP" paper acce…☆22Updated last year
- ☆44Updated last year
- ☆93Updated 3 months ago
- Simple and scalable tools for data-driven pretraining data selection.☆24Updated 3 months ago