Overview

Most books teach you how to build LLMs from scratch or deploy them via APIs. This book does uses guided machine learning projects to teach you how to understand, visualize, and investigate LLMs including GPT and BERT. Key Features Each project is built around three learning goals: machine learning techniques, LLM mechanisms, and Python coding with data visualization. This is not a dense theoretical textbook; it's hands-on, practical, and project-oriented. You will learn how to measure, visualize, and manipulate the internal components of LLMs directly. Book DescriptionThrough 50 hands-on, guided projects solved in Python, you will investigate the internal mechanisms of large language models by treating their hidden states, attention patterns, and embeddings as data to analyze. Rather than accepting LLMs as black boxes, you will open them up, examine what's inside, and run experiments to understand why they behave the way they do. All projects are based on Python (using libraries such as NumPy, PyTorch, statsmodels, scikit-learn, Matplotlib, Pandas, and Seaborn) and come with full solutions and partial solution notebook files, so you can practice and improve your skills in data science, deep learning, data visualization, and scientific and statistical coding.What you will learn Tokenization schemes and their statistical properties Embedding spaces: cosine similarity, semantic axes, and analogy vectors Output logits, softmax distributions, perplexity, and language biases Layer-by-layer transformer dynamics and dimensionality Attention mechanisms: QKV weights, attention scores, head ablation, and activation patching MLP subblocks: neuron tuning, mutual information, subspace analysis, and statistics-based causal manipulations Logit lens, indirect object identification, and causal tracing Who this book is forThis book is for data scientists, ML engineers, and researchers who want to go beyond surface-level understanding of LLMs. Prior Python experience is required. Familiarity with machine learning or deep learning is helpful but not required — techniques are introduced as they arise throughout the projects.

Full Product Details

9781808082559

Table of Contents

Reviews

Author Information

Mike X Cohen is an associate professor at the Radboud University Medical Center and the leader of the Synchronization in the Neural Systems research group. His research focuses on using state-of-the-art neuroscience methods to understand the mechanisms and implications of brain circuit dynamics and has been funded by government agencies in the US, Germany, Netherlands, and Europe, and by private institutions and medical centers. Mike has been teaching time series analysis, applied mathematics, and scientific programming for almost 20 years. He has published several textbooks on these topics and teaches a variety of real-life and online courses.

Tab Content 6

Countries Available