justinchiu / openlogprobsLinks
Extract full next-token probabilities via language model APIs
☆247Updated last year
Alternatives and similar repositories for openlogprobs
Users that are interested in openlogprobs are comparing it to the libraries listed below
Sorting:
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆207Updated 7 months ago
- Erasing concepts from neural representations with provable guarantees☆231Updated 6 months ago
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆200Updated this week
- ☆134Updated 4 months ago
- ☆123Updated last year
- Mechanistic Interpretability Visualizations using React☆272Updated 7 months ago
- Code to reproduce "Transformers Can Do Arithmetic with the Right Embeddings", McLeish et al (NeurIPS 2024)☆190Updated last year
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆207Updated last week
- A puzzle to learn about prompting☆132Updated 2 years ago
- A toolkit for describing model features and intervening on those features to steer behavior.☆195Updated 8 months ago
- ☆94Updated 3 months ago
- nanoGPT-like codebase for LLM training☆102Updated 2 months ago
- ☆285Updated last year
- Understand and test language model architectures on synthetic tasks.☆221Updated 2 weeks ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆119Updated 5 months ago
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆127Updated 2 years ago
- Draw more samples☆193Updated last year
- RuLES: a benchmark for evaluating rule-following in language models☆227Updated 5 months ago
- ☆28Updated last year
- Sparsify transformers with SAEs and transcoders☆595Updated this week
- Utilities for the HuggingFace transformers library☆70Updated 2 years ago
- Code for NeurIPS'24 paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'☆225Updated 2 weeks ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆57Updated 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
- PyTorch library for Active Fine-Tuning☆87Updated 5 months ago
- ☆274Updated last year
- Tools for understanding how transformer predictions are built layer-by-layer☆512Updated last year
- git extension for {collaborative, communal, continual} model development☆217Updated 8 months ago
- ☆233Updated 10 months ago