Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects
Paper • 2607.20596 • Published • 2
🏗️ Building on HF
Seonglae Cho
seonglae
AI & ML interests
NLP, Humanoid, AGI
Recent Activity
authored a paper 2 days ago
Are Single-Token Sparse Autoencoder Features Causally Necessary? Layer-Depth and SAE-Family Effects authored a paper 2 days ago
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder FeaturesOrganizations
authored 2
papers 2 days ago
upvoted a paper 2 days ago
updated a
Space 24 days ago
updated 7
Spaces 29 days ago
Control Reinforcement Learning
🎛
Explore LLM token decisions with feature‑driven visualizations
PaaT: Probe as a Tool for Proprioceptive Language Agents
🔀
CorrSteer: Correlation-Based Steering of Language Models via Sparse Autoencoders
🧭
4
Steer language model output by clicking visual layers
OptimismBench
🎲
Confidence Manifold
🧭
AgentRoom
🏠
Watch two AI agents code together in a shared workspace
Agent State Graph — Dashboard
📊
published 3
Spaces 29 days ago
published 2
Spaces about 1 month ago
updated a
dataset about 1 month ago
upvoted a collection about 1 month ago
published a
dataset 2 months ago
updated a
dataset 3 months ago