apartresearch / Neuron2GraphLinks
Tools for exploring Transformer neuron behaviour, including input pruning and diversification.
☆20Updated last year
Alternatives and similar repositories for Neuron2Graph
Users that are interested in Neuron2Graph are comparing it to the libraries listed below
Sorting:
- ☆27Updated 2 years ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated last year
- Interpretable text embeddings by asking LLMs yes/no questions (NeurIPS 2024)☆42Updated 9 months ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆188Updated 2 years ago
- ☆98Updated 4 months ago
- Code for 'Emergent Analogical Reasoning in Large Language Models'☆51Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 2 years ago
- ☆106Updated 6 months ago
- ☆138Updated last month
- Experiments and code to generate the GINC small-scale in-context learning dataset from "An Explanation for In-context Learning as Implici…☆108Updated last year
- ☆68Updated 2 years ago
- Google Research☆45Updated 2 years ago
- Discovering Data-driven Hypotheses in the Wild☆104Updated 2 months ago
- ☆14Updated last year
- Dataset and evaluation suite enabling LLM instruction-following for scientific literature understanding.☆40Updated 5 months ago
- Sparse and discrete interpretability tool for neural networks☆63Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ⚓️ Repository for the "Thought Anchors: Which LLM Reasoning Steps Matter?" paper.☆73Updated last week
- CausalGym: Benchmarking causal interpretability methods on linguistic tasks☆46Updated 9 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- ☆21Updated 9 months ago
- we got you bro☆36Updated last year
- Temporal Neural Networks☆17Updated last month
- ☆73Updated last year
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆18Updated last year
- ☆23Updated last year
- A repository for transformer critique learning and generation☆90Updated last year
- A library for efficient patching and automatic circuit discovery.☆76Updated last month
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆89Updated last year
- Sparse Autoencoder Training Library☆54Updated 4 months ago