EleutherAI / features-across-timeLinks
Understanding how features learned by neural networks evolve throughout training
☆41Updated last year
Alternatives and similar repositories for features-across-time
Users that are interested in features-across-time are comparing it to the libraries listed below
Sorting:
- Sparse and discrete interpretability tool for neural networks☆64Updated last year
- ☆68Updated last year
- Evaluation of neuro-symbolic engines☆41Updated last year
- Minimum Description Length probing for neural network representations☆20Updated last year
- ☆112Updated 11 months ago
- Official Repository of Pretraining Without Attention (BiGS), BiGS is the first model to achieve BERT-level transfer learning on the GLUE …☆116Updated last year
- Yet another random morning idea to be quickly tried and architecture shared if it works; to allow the transformer to pause for any amount…☆53Updated 2 years ago
- Experiments for efforts to train a new and improved t5☆76Updated last year
- gzip Predicts Data-dependent Scaling Laws☆34Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaine…☆40Updated 2 years ago
- Codebase for Context-aware Meta-learned Loss Scaling (CaMeLS). https://arxiv.org/abs/2305.15076.☆25Updated 2 years ago
- Codes and files for the paper Are Emergent Abilities in Large Language Models just In-Context Learning☆33Updated last year
- Engineering the state of RNN language models (Mamba, RWKV, etc.)☆32Updated last year
- ☆18Updated last year
- Google Research☆46Updated 3 years ago
- ☆57Updated 2 years ago
- Shaping capabilities with token-level pretraining data filtering☆75Updated 2 weeks ago
- Implementation of Influence Function approximations for differently sized ML models, using PyTorch☆16Updated 2 years ago
- Anchored Preference Optimization and Contrastive Revisions: Addressing Underspecification in Alignment☆61Updated last year
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆59Updated 2 years ago
- Code for PHATGOOSE introduced in "Learning to Route Among Specialized Experts for Zero-Shot Generalization"☆91Updated last year
- ☆24Updated last year
- Automatically take good care of your preemptible TPUs☆37Updated 2 years ago
- Synthetic data generation and benchmark implementation for "Episodic Memories Generation and Evaluation Benchmark for Large Language Mode…☆63Updated 4 months ago
- ☆36Updated 3 years ago
- ☆37Updated 2 years ago
- Embedding Recycling for Language models☆38Updated 2 years ago
- ☆59Updated 2 months ago
- Universal Neurons in GPT2 Language Models☆30Updated last year
- Notebooks accompanying Anthropic's "Toy Models of Superposition" paper☆135Updated 3 years ago