apartresearch / Neuron2Graph
Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
☆19Updated last year
Alternatives and similar repositories for Neuron2Graph:
Users that are interested in Neuron2Graph are comparing it to the libraries listed below
- Universal Neurons in GPT2 Language Models☆27Updated 7 months ago
- ☆26Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- A repository for transformer critique learning and generation☆88Updated last year
- Open source replication of Anthropic's Crosscoders for Model Diffing☆28Updated 2 months ago
- Replicating O1 inference-time scaling laws☆70Updated last month
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆57Updated last year
- ☆39Updated 3 years ago
- A virtual environment for developing and evaluating automated scientific discovery agents.☆117Updated last week
- ☆76Updated 6 months ago
- ☆14Updated 9 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆66Updated last year
- The repository contains code for Adaptive Data Optimization☆21Updated last month
- Q-Probe: A Lightweight Approach to Reward Maximization for Language Models☆40Updated 7 months ago
- Discovering Data-driven Hypotheses in the Wild☆51Updated 2 months ago
- Sparse Autoencoder Training Library☆38Updated 2 months ago
- Evaluation of neuro-symbolic engines☆34Updated 5 months ago
- Super fast implementations of common benchmark text world games☆44Updated last month
- Repository for the paper Stream of Search: Learning to Search in Language☆119Updated 5 months ago
- ☆44Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆64Updated 7 months ago
- Dataset and benchmark for assessing LLMs in translating natural language descriptions of planning problems into PDDL☆48Updated 3 months ago
- [ACL 2024] <Large Language Models for Automated Open-domain Scientific Hypotheses Discovery>. It has also received the best poster award …☆36Updated 2 months ago
- ☆90Updated this week
- Large language models (LLMs) made easy, EasyLM is a one stop solution for pre-training, finetuning, evaluating and serving LLMs in JAX/Fl…☆64Updated 5 months ago
- Sparse and discrete interpretability tool for neural networks☆58Updated 11 months ago
- Scaling scaling laws with board games.☆45Updated last year
- Tree prompting: easy-to-use scikit-learn interface for improved prompting.☆35Updated last year
- Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning☆33Updated last week
- Measuring the situational awareness of language models☆33Updated 11 months ago