# Alignment Research Engineer Accelerator This is where the ARENA course conten > Source: > Published: 2026-09-12 14:05:50+00:00 Alignment Research Engineer Accelerator This is where the ARENA course content is hosted. For more information about the ARENA program, including upcoming cohorts and how to apply, visit [arena.education](https://arena.education). ## Fundamentals Build your foundation in deep learning, from prerequisites through CNNs, optimization, backpropagation, and generative models. ## Interpretability Dive deep into language model interpretability, from linear probes and SAEs to circuit analysis and toy models. ## RL Take a whirlwind tour through RL, starting from tabular learning and Atari, and ending with some of the cutting-edge techniques used in current LLM post-training. ## Evals Learn to build and run evaluations for large language models, including dataset generation and LLM agents. ## Alignment Science Case studies in misalignment, covering a range of topics and techniques (both white-box and black-box). [0.0 Prerequisites Essential PyTorch basics, einops/einsum libraries, and tensor manipulation fundamentals.](/chapter0_fundamentals/00_prereqs/intro) [0.1 Ray Tracing Learn batched operations and linear algebra by rendering 3D meshes with raytracing.](/chapter0_fundamentals/01_ray_tracing/intro) [0.2 CNNs & ResNets Build neural networks from scratch, from MNIST classifiers to ResNets for CIFAR-10.](/chapter0_fundamentals/02_cnns/intro) [0.3 Optimization Implement SGD, RMSprop & Adam optimizers, and use Weights & Biases for experiment tracking.](/chapter0_fundamentals/03_optimization/intro) [0.4 Backpropagation Build your own autograd system from scratch and train MLPs with custom backpropagation.](/chapter0_fundamentals/04_backprop/intro) [0.5 VAEs & GANs Implement GANs and VAEs, foundational architectures for generative image models.](/chapter0_fundamentals/05_vaes_gans/intro) [1.1 Transformers from Scratch Build a transformer from scratch and load pretrained GPT-2 weights.](/chapter1_transformer_interp/01_transformers/intro) [1.2 Intro to Mech Interp Learn TransformerLens to extract activations, apply hooks & find important attention heads.](/chapter1_transformer_interp/02_intro_mech_interp/intro) [1.3.1 Linear Probes Train linear probes to detect deception in a model playing the game Coup.](/chapter1_transformer_interp/11_probing/intro) [1.3.2 Function Vectors & Model Steering Steer model behaviour using activation interventions and the nnsight library.](/chapter1_transformer_interp/12_function_vectors/intro) [1.3.3 Interpretability with SAEs Use SAEs to decompose LLM activation space, monitor cognition & steer behaviour.](/chapter1_transformer_interp/13_saes/intro) [1.3.4 Activation Oracles Implement activation oracles to reveal hidden knowledge and uncover forward-predictions.](/chapter1_transformer_interp/14_activation_oracles/intro) [1.4.1 Indirect Object Identification Reverse-engineer the IOI circuit in GPT-2 small following 'Interpretability in the Wild'.](/chapter1_transformer_interp/21_ioi/intro) [1.4.2 SAE Circuits Apply SAEs to circuit analysis, decomposing computations and tracing features through layers.](/chapter1_transformer_interp/22_sae_circuits/intro) [1.5.1 Balanced Bracket Classifier Reverse-engineer the algorithm learned by a bracket-balancing transformer.](/chapter1_transformer_interp/31_brackets/intro) [1.5.2 Grokking & Modular Arithmetic Discover Fourier circuits in modular arithmetic models and observe grokking in action.](/chapter1_transformer_interp/32_grokking/intro) [1.5.3 OthelloGPT Investigate emergent world representations in a GPT model trained on Othello games.](/chapter1_transformer_interp/33_othellogpt/intro) [1.5.4 Superposition & SAEs Replicate Anthropic's superposition paper and train SAEs to recover features.](/chapter1_transformer_interp/34_superposition/intro) [Monthly Algorithmic Problems 7 algorithmic challenges to test your interpretability skills in hackathon format.](/chapter1_transformer_interp/monthly_algorithmic/intro) [2.1 Intro to RL RL fundamentals: MDPs, policies, value functions, and multi-armed bandits.](/chapter2_rl/01_intro_rl/intro) [2.2.1 DQN Implement DQN for CartPole and beyond.](/chapter2_rl/21_dqn/intro) [2.2.2 VPG Implement Vanilla Policy Gradient for CartPole.](/chapter2_rl/22_vpg/intro) [2.3 PPO Build a PPO agent from scratch and train it to master CartPole.](/chapter2_rl/03_ppo/intro) [2.4 RLHF Implement RLHF end-to-end, applying PPO to language model finetuning.](/chapter2_rl/04_rlhf/intro) [2.5 MCTS & AlphaZero Implement MCTS and AlphaZero to train agents for complex games.](/chapter2_rl/05_mcts_alphazero/intro) [3.1 Intro to Evals Design threat models and specifications for evaluating model properties.](/chapter3_llm_evals/01_intro_evals/intro) [3.2 Dataset Generation Use LLMs to generate and refine high-quality evaluation datasets.](/chapter3_llm_evals/02_dataset_gen/intro) [3.3 Running Evals with Inspect Run standardised LLM evaluations using UK AISI's Inspect library.](/chapter3_llm_evals/03_running_evals/intro) [3.4 LLM Agents Build LLM agents with scaffolding to play Wikipedia Racing and other tasks.](/chapter3_llm_evals/04_llm_agents/intro) [3.5 AI Control Learn to monitor and control AI systems in a simulated environment.](/chapter3_llm_evals/05_ai_control/intro) [4.1 Emergent Misalignment Study emergent misalignment in finetuned models.](/chapter4_alignment_science/1_emergent_misalignment/intro) [4.2 Science of Misalignment Two case studies in black-box investigation to understand and characterize seemingly misaligned behaviour.](/chapter4_alignment_science/2_science_misalignment/intro) [4.3 Interpreting Reasoning Models Apply interpretability techniques to chain-of-thought reasoning models.](/chapter4_alignment_science/3_reasoning_models/intro) [4.4 LLM Psychology & Persona Vectors Explore persona vectors and psychological properties of language models.](/chapter4_alignment_science/4_persona_vectors/intro) [4.5 Investigator Agents Use AI agents for investigating model behaviours (including petri & bloom).](/chapter4_alignment_science/5_investigator_agents/intro)