Transluce
232 posts
@TransluceAI
Open and scalable technology for understanding AI systems.
Is your LM secretly an SAE? Most circuit-finding interpretability methods use learned features rather than raw activations, based on the belief that neurons do not cleanly decompose computation. In our new work, we show MLP neurons actually do support sparse, faithful circuits!
Is your LM secretly an SAE? Most circuit-finding interpretability methods use learned features rather than raw activations, based on the belief that neurons do not cleanly decompose computation. In our new work, we show MLP neurons actually do support sparse, faithful circuits!
Transluce is running our end-of-year fundraiser for 2025. This is our first public fundraiser since launching late last year.
Transluce is running our end-of-year fundraiser for 2025. This is our first public fundraiser since launching late last year.
We can train models on maximizing how well they explain LLMs to humans 🤯@cogconfluence paraphrased. Mechanistic Interpretability Workshop #NeurIPS2025.
