Does Transformer Interpretability Transfer to RNNs?#RNN#Transformers#Large Language Models#Paper#PDF#EleutherAI·arxiv.org·Apr 10, 2024Does Transformer Interpretability Transfer to RNNs?
Neural Networks Learn Statistics of Increasing ComplexityDownload PDF#Machine Learning#Neural Networks#Paper#PDF#EleutherAI·arxiv.org·Feb 9, 2024Neural Networks Learn Statistics of Increasing Complexity
Llemma: An Open Language Model For Mathematics#Mathematics#Large Language Models#Paper#PDF#EleutherAI·arxiv.org·Oct 17, 2023Llemma: An Open Language Model For Mathematics
Can Transformers Learn to Solve Problems Recursively?#Transformers#Problem-Solving#Recursion#Paper#PDF#EleutherAI·arxiv.org·May 27, 2023Can Transformers Learn to Solve Problems Recursively?
Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling#EleutherAI#Science#Research#Paper#PDF#Large Language Models·arxiv.org·Apr 10, 2023Pythia: A Suite for Analyzing Large Language Models Across Training and Scaling