koayon / atp_starLinks
PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)
☆20Updated 9 months ago
Alternatives and similar repositories for atp_star
Users that are interested in atp_star are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆82Updated 10 months ago
- Code to reproduce key results accompanying "SAEs (usually) Transfer Between Base and Chat Models"☆12Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- ☆107Updated 8 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆128Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- Code for my NeurIPS 2024 ATTRIB paper titled "Attribution Patching Outperforms Automated Circuit Discovery"☆43Updated last year
- A library for mechanistic anomaly detection☆22Updated 9 months ago
- ☆92Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆74Updated 2 weeks ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆28Updated last year
- A tiny easily hackable implementation of a feature dashboard.☆15Updated last month
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆218Updated last week
- ☆19Updated 6 months ago
- Engine for collecting, uploading, and downloading model activations☆24Updated 6 months ago
- Sparse probing paper full code.☆62Updated last year
- ☆126Updated last year
- ☆57Updated 3 months ago
- A collection of different ways to implement accessing and modifying internal model activations for LLMs☆19Updated last year
- ☆191Updated last week
- Official Code for our paper: "Language Models Learn to Mislead Humans via RLHF""☆17Updated last year
- ☆54Updated 11 months ago
- ☆23Updated last week
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆19Updated last year
- ☆81Updated 8 months ago