🏗️ Building on HF
Seonglae Cho
seonglae
AI & ML interests
NLP, Humanoid, AGI
Recent Activity
upvoted a paper about 19 hours ago
Control Reinforcement Learning: Interpretable Token-Level Steering of LLMs via Sparse Autoencoder Features authored a paper 2 days ago
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model Judgment upvoted a paper 2 days ago
OptimismBench: Forecasting Bias and the Alignment Effect in Language Model JudgmentOrganizations
spaces 10
Running
Automata from Agent Traces
🔁
Explore LLM agent behavior as an interactive state machine
Paused
OptimismBench
🎲
Sleeping
AgentRoom
🏠
Watch two AI agents code together in a shared workspace
Paused
Confidence Manifold
🧭
Paused
Control Reinforcement Learning
🎛
Explore LLM token decisions with feature‑driven visualizations
Running
4
CorrSteer: Correlation-Based Steering of Language Models via Sparse Autoencoders
🧭
Steer language model output by clicking visual layers
models 13
seonglae/Llama-3.1-8B-sae
Updated
seonglae/Llama-3.2-1B-sae
Updated
seonglae/Llama-3.2-3B-sae
Updated
seonglae/gemma-2-2b-sae
Updated
seonglae/yokhal-md
Text Generation • 3B • Updated • 8
seonglae/resrer-bart-base
0.1B • Updated • 4
seonglae/resrer-pegasus-x
0.3B • Updated • 4
seonglae/rtsum
Updated • 4
seonglae/llama-2-13b-chat-hf-gptq
Text Generation • Updated • 4
seonglae/llama-2-7b-chat-hf-gptq
Text Generation • Updated • 6
datasets 18
seonglae/OptimismBench
Preview • Updated • 21
seonglae/streamwriter-100k
Viewer • Updated • 74.8k • 121
seonglae/lc-ode1
Viewer • Updated • 136k • 15
seonglae/math-pde
Viewer • Updated • 7.17k • 121
seonglae/faithful-pythia1.4b
Viewer • Updated • 312k • 12
seonglae/faithful-pythia-6.9b
Viewer • Updated • 200k • 37
seonglae/faithful-llama3.2-1b
Viewer • Updated • 276k • 36
seonglae/faithful-gpt2-small
Viewer • Updated • 162k • 17
seonglae/faithful-gemma2-2b
Viewer • Updated • 208k • 50
seonglae/faithful-llama3.2-3b
Viewer • Updated • 263k • 26