ckkissane / sae-transfer
Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"
☆11Updated 8 months ago
Alternatives and similar repositories for sae-transfer:
Users that are interested in sae-transfer are comparing it to the libraries listed below
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆18Updated 2 months ago
- ☆18Updated last year
- A library for efficient patching and automatic circuit discovery.☆62Updated last month
- 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 2 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆49Updated 5 months ago
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆42Updated 5 months ago
- Multi-Layer Sparse Autoencoders (ICLR 2025)☆22Updated last month
- ☆46Updated last year
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆73Updated 4 months ago
- https://footprints.baulab.info☆17Updated 5 months ago
- Universal Neurons in GPT2 Language Models☆27Updated 10 months ago
- Algebraic value editing in pretrained language models☆63Updated last year
- Exploration of automated dataset selection approaches at large scales.☆34Updated last month
- ☆33Updated last month
- Is In-Context Learning Sufficient for Instruction Following in LLMs? [ICLR 2025]☆29Updated 2 months ago
- Official code repo for paper "Great Memory, Shallow Reasoning: Limits of kNN-LMs"☆22Updated 7 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆62Updated last week
- Sparse Autoencoder Training Library☆47Updated 5 months ago
- Code for ICLR 2025 Paper "What is Wrong with Perplexity for Long-context Language Modeling?"☆47Updated last week
- ☆38Updated last year
- ☆12Updated 9 months ago
- Repository for NPHardEval, a quantified-dynamic benchmark of LLMs☆52Updated last year
- ☆82Updated 7 months ago
- ☆16Updated 10 months ago
- [NeurIPS 2024 Spotlight] Code and data for the paper "Finding Transformer Circuits with Edge Pruning".☆47Updated 3 weeks ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆67Updated 9 months ago
- Mamba support for transformer lens☆16Updated 6 months ago
- ☆80Updated 4 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 10 months ago
- ☆21Updated 2 months ago