jxbz / entropix
π° Computing the information content of trained neural networks
β21Updated 3 years ago
Alternatives and similar repositories for entropix:
Users that are interested in entropix are comparing it to the libraries listed below
- Minimum Description Length probing for neural network representationsβ19Updated 3 months ago
- β29Updated last year
- PyTorch implementation for "Long Horizon Temperature Scaling", ICML 2023β20Updated last year
- Implements EvoNorms B0 and S0 as proposed in Evolving Normalization-Activation Layers.β11Updated 5 years ago
- β18Updated 2 years ago
- Efficient Scaling laws and collaborative pretraining.β16Updated 3 months ago
- Code for experiments on self-prediction as a way to measure introspection in LLMsβ13Updated 4 months ago
- β17Updated 2 years ago
- β15Updated last year
- An attempt to merge ESBN with Transformers, to endow Transformers with the ability to emergently bind symbolsβ15Updated 3 years ago
- Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks" [to appear at ICLR 2025]β19Updated last month
- Latest Weight Averaging (NeurIPS HITY 2022)β30Updated last year
- Python package for generating datasets to evaluate reasoning and retrieval of large language modelsβ18Updated last week
- β15Updated 3 months ago
- Understanding how features learned by neural networks evolve throughout trainingβ34Updated 6 months ago
- Investigate the speed of adaptation of structural causal modelsβ16Updated 4 years ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classificationβ11Updated last year
- Aioli: A unified optimization framework for language model data mixingβ25Updated 3 months ago
- PyTorch Implementation of the paper "MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training"β23Updated 2 weeks ago
- This repo contains code for the paper: "Can Foundation Models Help Us Achieve Perfect Secrecy?"β24Updated 2 years ago
- Official code for the paper: "Metadata Archaeology"β19Updated last year
- Efficient Dictionary Learning with Switch Sparse Autoencoders (SAEs)β22Updated 5 months ago
- Repository for the code and dataset for the paper: "Have LLMs Advanced enough? Towards Harder Problem Solving Benchmarks For Large Languβ¦β39Updated last year
- [Oral; Neurips OPT2024 ] ΞΌLO: Compute-Efficient Meta-Generalization of Learned Optimizersβ12Updated last month
- Experiments on GPT-3's ability to fit numerical models in-context.β14Updated 2 years ago
- The code repository associated with the NeurIPS 2020 paper: "Towards Neural Programming Interfaces"β13Updated 2 years ago
- Implementation of N-Grammer in Flaxβ17Updated 2 years ago
- code for paper "Accessing higher dimensions for unsupervised word translation"β21Updated last year
- β27Updated last year
- β26Updated 2 years ago