Author: Shuyang
-
Large Language models (LLMs) have witnessed impressive progress and these large models can do a…
6 min read -
Disentangle features in complex Neural Network with superpositions
6 min read -
When there are more features than model dimensions
7 min read -
Existence of under-trained and unused tokens and Identification Techniques using GPT-2 Small as an Example
8 min read -
A concrete case study
7 min read -
A step-by-step guide
7 min read -
How we build a PINN for inviscid Burgers Equation with shock formulation
6 min read -
Mechanistic Interpretability on prediction of repeated tokens
8 min read -
with LangChain’s Self-Querying based on a customized CSV Loader
10 min read