Viraj Sharma
I am a passionate technologist with a strong interest in Python, artificial intelligence and Edge computing. I am currently studying in Class 9 at Presidium School, Delhi, INDIA. I have worked in areas such as torch.nn visualization, Anthropic technologies (MCP, Skills), large concept models, and TensorCore/CUDA benchmarks, Edge AI on raspbrry pi running small models with sensors. Recently I have been working on XAI (AI explaianability) and putting my work as a project on my AI Lab - modelrecon.com. As an active member of the Python community and AI communities, I enjoy learning from experienced developers and sharing my insights with others. I attend major tech events including PyCons, Linux Fests, OS Summits, GDG events, p99conf, and various AI conferences, where I actively present my projects and ideas.
@virajsharma2000
https://github.com/modelrecon; https://github.com/safety-research/circuit-tracer
Session
In this talk, I propose to discuss the problem of building explainable AI with the two approaches - causal vs correlational. I will talk about what mech interp in LLMs. As a way to understand how models answer questions by looking inside them and checking which neurons activate when. I will discuss Anthropic's open sourced a python module - circuit-tracer, the Neuronpedia portal , will also talk about my own work with "activation cube" data structure (this is not a standard - I came up with it)