ManySpace
English Giriş yap Kayıt ol

Yapay ZekâUzmanlıkAIML-INT-006

Superposition and Sparse Dictionary Features

Networks pack more features than dimensions; sparse autoencoders try to recover interpretable features.

Bu konunun henüz Türkçe çevirisi yok, bu yüzden İngilizce gösteriliyor.

Zorluk
5 / 5
Önem
3 / 5
Çalışma süresi
1–2 sa
Çalışma türü
Karma

Neden önemli

The learner can explain superposition with a toy model and describe how a sparse autoencoder's sparsity penalty trades reconstruction for interpretability.

Bu konuya giden rota

Rota AIML-INT-006
Doğal Sayılar What Is a Model? Değişkenler ve Sabitler Learning from Data Tasks: Regression, Classification, and Beyond Features and Targets Doğrusal Denklemleri Çözme Fonksiyon Gösterimi ve Bileşke Datasets and Splits Classification Framing Numeric and Categorical Data Linear Regression I: Prediction and Residuals Embeddings Kompleks Sayılar Scores and Logits Encoding Categories Loss and Fitting: Squared Error Similarity in Vector Space Temel Trigonometrik Oranlar Sigmoid and Probabilities Multiclass Scores and Softmax The Artificial Neuron Doğrusal Regresyon II: En Küçük Kareler Uydurma Distributed Representations Query, Key, Value Polinom Fonksiyonlar Logistic Regression Overfitting and Underfitting Activation Functions Principal Component Analysis Word Embeddings Similarity Scores Türevin Tanımı Türev Alma Kuralları Regularization: Ridge The Multilayer Perceptron Latent Representations Weighted Aggregation Contextual Representations Zincir Kuralı Regularization: Lasso and Sparsity Forward Propagation Probing Representations Self-Attention Computational Graphs The Attention Block The Chain Rule in Neural Nets The Causal Transformer Backpropagation Reading a Transformer Autoencoders Mechanistic Interpretability: Circuits Superposition and Sparse Dictionary Features