Sparse Auto-Encoders (SAEs) for Mechanistic Interpretability Collection A compilation of sparse auto-encoders trained on large language models. • 37 items • Updated 22 days ago • 20
Running 97 The Eiffel Tower Llama 📝 97 Explore the Eiffel Tower Llama experiment with open-source models
Running on Zero 7 The Eiffel Tower Llama Demo 💬 7 Steering a large language model using sparse autoencoders
Running on Zero 7 The Eiffel Tower Llama Demo 💬 7 Steering a large language model using sparse autoencoders
Running 97 The Eiffel Tower Llama 📝 97 Explore the Eiffel Tower Llama experiment with open-source models
Running on Zero 7 The Eiffel Tower Llama Demo 💬 7 Steering a large language model using sparse autoencoders