ResearchTrend.AI
TracrBench: Generating Interpretability Testbeds with Large Language Models

TracrBench: Generating Interpretability Testbeds with Large Language Models

Hannes Thurnherr
Jérémy Scheurer
ArXivPDFHTML

Papers citing "TracrBench: Generating Interpretability Testbeds with Large Language Models"

3 / 3 papers shown
Title
Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
Evaluating Explanations: An Explanatory Virtues Framework for Mechanistic Interpretability -- The Strange Science Part I.ii
Kola Ayonrinde
Louis Jaburi
XAI
55
1
0
02 May 2025
Neural Decompiling of Tracr Transformers
Neural Decompiling of Tracr Transformers
Hannes Thurnherr
Kaspar Riesen
ViT
15
1
0
29 Sep 2024
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
InterpBench: Semi-Synthetic Transformers for Evaluating Mechanistic Interpretability Techniques
Rohan Gupta
Iván Arcuschin
Thomas Kwa
Adrià Garriga-Alonso
37
2
0
19 Jul 2024