Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability A compilation of sparse auto-encoders trained on large language models. EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k Updated Jan 26, 2025 • 7 • 7 EleutherAI/skip-transcoder-DeepSeek-R1-Distill-Qwen-1.5B-65k Updated Jan 26, 2025 • 7 • 4 EleutherAI/sae-pythia-70m-32k Updated Aug 5, 2024 EleutherAI/sae-pythia-160m-32k Updated Aug 5, 2024 • 1
Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability A compilation of sparse auto-encoders trained on large language models. EleutherAI/sae-DeepSeek-R1-Distill-Qwen-1.5B-65k Updated Jan 26, 2025 • 7 • 7 EleutherAI/skip-transcoder-DeepSeek-R1-Distill-Qwen-1.5B-65k Updated Jan 26, 2025 • 7 • 4 EleutherAI/sae-pythia-70m-32k Updated Aug 5, 2024 EleutherAI/sae-pythia-160m-32k Updated Aug 5, 2024 • 1
Running 108 The Eiffel Tower Llama 📝 Explore the Eiffel Tower Llama experiment with open-source models