3 citations · 3 across the 7 of their papers we have counts for
3 papers · 1 filter
Evaluating Sparse Autoencoders for Monosemantic Representation
Moghis Fereidouni, Muhammad Umair Haider, Peizhong Ju +1
A key barrier to interpreting large language models is polysemanticity, where neurons activate for multiple unrelated concepts. Sparse autoencoders (SAEs) have been proposed to mit…
Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution
Muhammad Umair Haider, Hammad Rizwan, Hassan Sajjad +2
Pervasive polysemanticity in large language models (LLMs) undermines discrete neuron-concept attribution, posing a significant challenge for model interpretation and control. We sy…
Teacher-Class Network: A Neural Network Compression Mechanism
Shaiq Munir Malik, Muhammad Umair Haider, Mohbat Tharani +2
To reduce the overwhelming size of Deep Neural Networks (DNN) teacher-student methodology tries to transfer knowledge from a complex teacher network to a simple student network. We…