mechanistic-interpretability-grokking / progress-measures-paperLinks
☆69Updated 3 years ago
Alternatives and similar repositories for progress-measures-paper
Users that are interested in progress-measures-paper are comparing it to the libraries listed below
Sorting:
- ☆126Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆129Updated 3 years ago
- ☆247Updated last year
- Sparse Autoencoder Training Library☆55Updated 5 months ago
- A library for efficient patching and automatic circuit discovery.☆78Updated 3 months ago
- 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
- ☆107Updated 8 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆82Updated 10 months ago
- ☆128Updated last year
- ☆92Updated last year
- ☆74Updated 2 weeks 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
- ☆109Updated 8 months ago
- ☆131Updated this week
- 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
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Attribution-based Parameter Decomposition☆31Updated 4 months ago
- ☆190Updated last week
- ☆27Updated 2 years ago
- Emergent world representations: Exploring a sequence model trained on a synthetic task☆191Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆136Updated 4 months ago
- ☆240Updated last year
- Evaluate interpretability methods on localizing and disentangling concepts in LLMs.☆56Updated last year
- ☆23Updated 8 months ago
- ☆23Updated last year
- The accompanying code for "Transformer Feed-Forward Layers Are Key-Value Memories". Mor Geva, Roei Schuster, Jonathan Berant, and Omer Le…☆97Updated 4 years ago
- Algebraic value editing in pretrained language models☆66Updated last year
- Universal Neurons in GPT2 Language Models☆30Updated last year
- ☆83Updated 2 years ago
- [NeurIPS 2023] Learning Transformer Programs☆162Updated last year