ML Understanding

Channel: #ml-understanding
ML Understanding is a channel dedicated to unraveling the inner workings of neural networks through the lens of mechanistic interpretability. We'll explore how features and circuits emerge, how techniques like probing, sparse autoencoders, and causal analysis help decode model behavior, and how these insights impact AI safety, model editing, and generation. Whether you're curious about superposition, polysemanticity, or practical evaluation methods, this is the space to dive deep, share, and grow together as researchers. We focus on making our sessions beginner-friendly, discussing simple as well as complex concepts in depth, and believe there are no stupid questions😀

Leads:
Akanksha:  akankshanc on Discord and X
Kabir: kabir25 on Discord and X
Ryan: ryanr158 on Discord and ryanrosario_ on X