Curt Tigges
4 papers · 2024–2025 · 4 venues · across top CS/AI venues
Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.
Achievements
Jump to papers ↓
🌍
Conference Polyglot · Bronze
🌉
Interdisciplinary Bridge · Bronze
Venues
Top co-authors
Research topics
Keywords
large language model
(3)
sparse autoencoder
(2)
interpretability
(1)
attention mechanism
(1)
feature disentanglement
(1)
circuit analysis
(1)
feature decomposition
(1)
mechanistic interpretability
(1)
model scaling
(1)
causal intervention
(1)
linear representation
(1)
latent feature
(1)
activation space
(1)
neural network
(1)
unlearning
(1)
meta learning
(1)
saebench
(1)
sentiment analysis
(1)
Papers
SAEBench: A Comprehensive Benchmark for Sparse Autoencoders in Language Model Interpretability
ICML 2025
Sparse Autoencoders Do Not Find Canonical Units of Analysis
ICLR 2025
Language Models Linearly Represent Sentiment
EMNLP 2024
LLM Circuit Analyses Are Consistent Across Training and Scale
NeurIPS 2024