EleutherAI / features-across-time
Understanding how features learned by neural networks evolve throughout training
☆34Updated 6 months ago
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:
- Minimum Description Length probing for neural network representations☆19Updated 3 months ago
- Universal Neurons in GPT2 Language Models☆29Updated 11 months ago
- Sparse and discrete interpretability tool for neural networks☆62Updated last year
- gzip Predicts Data-dependent Scaling Laws☆35Updated 11 months ago
- Efficient Scaling laws and collaborative pretraining.☆16Updated 3 months ago
- ☆24Updated 3 months ago
- ☆35Updated last year
- ☆38Updated last week
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]☆19Updated 2 months ago
- ☆26Updated 2 years ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆79Updated last month
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023☆20Updated last year
- Evaluation of neuro-symbolic engines☆35Updated 9 months ago
- ☆36Updated 2 years ago
- ☆68Updated 9 months ago
- ☆31Updated 4 months ago
- ☆29Updated last year
- Aioli: A unified optimization framework for language model data mixing☆25Updated 3 months ago
- Code Release for "Broken Neural Scaling Laws" (BNSL) paper☆58Updated last year
- ☆27Updated last year
- ☆53Updated 7 months ago
- Experiments for efforts to train a new and improved t5☆77Updated last year
- ☆19Updated 10 months ago
- ☆22Updated 7 months ago
- ☆49Updated last year
- This repo is based on https://github.com/jiaweizzhao/GaLore☆27Updated 7 months ago
- Official implementation of "BERTs are Generative In-Context Learners"☆27Updated 2 months ago
- Lottery Ticket Adaptation☆39Updated 5 months ago
- Memory Mosaics are networks of associative memories working in concert to achieve a prediction task.☆41Updated 3 months ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆26Updated 11 months ago