RylanSchaeffer / Stanford-AI-Alignment-Double-Descent-TutorialLinks
Code for Arxiv Double Descent Demystified: Identifying, Interpreting & Ablating the Sources of a Deep Learning Puzzle
β57Updated last year
Alternatives and similar repositories for Stanford-AI-Alignment-Double-Descent-Tutorial
Users that are interested in Stanford-AI-Alignment-Double-Descent-Tutorial are comparing it to the libraries listed below
Sorting:
- Deep Networks Grok All the Time and Here is Whyβ37Updated last year
- π Code for : "CRAFT: Concept Recursive Activation FacTorization for Explainability" (CVPR 2023)β68Updated 2 years ago
- π Overcomplete is a Vision-based SAE Toolboxβ96Updated 3 months ago
- Sparse and discrete interpretability tool for neural networksβ64Updated last year
- Personal implementation of ASIF by Antonio Norelliβ26Updated last year
- Recycling diverse modelsβ46Updated 2 years ago
- Omnigrok: Grokking Beyond Algorithmic Dataβ62Updated 2 years ago
- β27Updated 2 years ago
- Decomposing and Editing Predictions by Modeling Model Computationβ138Updated last year
- ModelDiff: A Framework for Comparing Learning Algorithmsβ59Updated 2 years ago
- Unofficial implementation of Conformal Language Modeling by Quach et alβ29Updated 2 years ago
- Code for the paper: "No Zero-Shot Without Exponential Data: Pretraining Concept Frequency Determines Multimodal Model Performance" [NeurIβ¦β90Updated last year
- This repository includes code to reproduce the tables in "Loss Landscapes are All You Need: Neural Network Generalization Can Be Explaineβ¦β40Updated 2 years ago
- Implementation of the general framework for AMIE, from the paper "Towards Conversational Diagnostic AI", out of Google Deepmindβ68Updated last year
- Official code for the ICML 2024 paper "The Entropy Enigma: Success and Failure of Entropy Minimization"β53Updated last year
- Privacy backdoorsβ51Updated last year
- $100K or 100 Days: Trade-offs when Pre-Training with Academic Resourcesβ147Updated last month
- Understanding how features learned by neural networks evolve throughout trainingβ39Updated last year
- Uncertainty-aware representation learning (URL) benchmarkβ105Updated 7 months ago
- PyTorch library for Active Fine-Tuningβ93Updated last month
- This repository contains a Jax implementation of conformal training corresponding to the ICLR'22 paper "learning optimal conformal classiβ¦β129Updated 3 years ago
- Automatic identification of regions in the latent space of a model that correspond to unique concepts, namely to concepts with a semanticβ¦β14Updated last year
- Official repo of Progressive Data Expansion: data, code and evaluationβ29Updated last year
- β60Updated last year
- Official PyTorch Implementation for Meaning Representations from Trajectories in Autoregressive Models (ICLR 2024)β22Updated last year
- β66Updated 7 months ago
- β32Updated last year
- Portfolio REgret for Confidence SEquencesβ20Updated 10 months ago
- β53Updated last year
- β33Updated 9 months ago