JoshEngels / SAE-Probes
Code for reproducing our paper "Are Sparse Autoencoders Useful? A Case Study in Sparse Probing"
☆16Updated this week
Alternatives and similar repositories for SAE-Probes:
Users that are interested in SAE-Probes are comparing it to the libraries listed below
- This is the oficial repository for "Safer-Instruct: Aligning Language Models with Automated Preference Data"☆17Updated last year
- Code for reproducing our paper "Low Rank Adapting Models for Sparse Autoencoder Features"☆10Updated last month
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆62Updated this week
- ☆28Updated last year
- The repository contains code for Adaptive Data Optimization☆20Updated 3 months ago
- Lottery Ticket Adaptation☆38Updated 4 months ago
- Script for processing OpenAI's PRM800K process supervision dataset into an Alpaca-style instruction-response format☆27Updated last year
- ☆31Updated 2 months ago
- Aioli: A unified optimization framework for language model data mixing☆22Updated 2 months ago
- The official repository for SkyLadder: Better and Faster Pretraining via Context Window Scheduling☆23Updated last week
- ☆21Updated 5 months ago
- ☆60Updated 11 months ago
- ☆44Updated 10 months ago
- Minimum Description Length probing for neural network representations☆19Updated 2 months ago
- https://footprints.baulab.info☆17Updated 5 months ago
- A testbed for agents and environments that can automatically improve models through data generation.☆21Updated 3 weeks ago
- Official repository of "LiNeS: Post-training Layer Scaling Prevents Forgetting and Enhances Model Merging"☆24Updated 4 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆22Updated 7 months ago
- ☆32Updated 3 weeks ago
- Codebase for Instruction Following without Instruction Tuning☆33Updated 6 months ago
- In-Context Alignment: Chat with Vanilla Language Models Before Fine-Tuning☆34Updated last year
- Reference implementation for Reward-Augmented Decoding: Efficient Controlled Text Generation With a Unidirectional Reward Model☆42Updated last year
- Code for the arXiv preprint "The Unreasonable Effectiveness of Easy Training Data"☆46Updated last year
- ☆15Updated last month
- Knowledge Unlearning for Large Language Models☆22Updated 3 weeks ago
- ☆27Updated this week
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)☆21Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- ☆36Updated 6 months ago
- This repo is based on https://github.com/jiaweizzhao/GaLore☆26Updated 6 months ago