归档

2025  4

June  2

Thinking and Reasoning

June 30, 2025 · 3 min · 1225 words · Sirius

LLM Agents

June 28, 2025 · 1 min · 348 words · Sirius

February  2

Interpretability for Multimodal Models

February 25, 2025 · 5 min · 2272 words · Sirius

Circuit-tuning: A Mechanistic Approach for Identifying Parameter Redundancy and Fine-tuning Neural Networks

February 5, 2025 · 1 min · 3 words · Sirius

2024  4

September  2

一些语言学的梗和有意思的知识

September 27, 2024 · 3 min · 1381 words · Sirius

Possible Research Areas in Mechanistic Interpretability

September 6, 2024 · 6 min · 2756 words · Sirius

August  2

Exploring Emotional Features in GPT2-Small

August 29, 2024 · 6 min · 1114 words · Sirius

A Brief Introduction to Mechanistic Interpretability Research

August 28, 2024 · 16 min · 3210 words · Sirius