|
gptkbp:instanceOf
|
Research Project
|
|
gptkbp:associatedWith
|
gptkb:OpenAI
gptkb:Anthropic
|
|
gptkbp:field
|
gptkb:Machine_Learning
gptkb:artificial_intelligence
|
|
gptkbp:focusesOn
|
gptkb:Neural_Networks
Transformer Models
Interpretability
|
|
gptkbp:goal
|
Reverse Engineering Neural Networks
Understanding Internal Mechanisms of Transformers
|
|
https://www.w3.org/2000/01/rdf-schema#label
|
Transformer Circuits
|
|
gptkbp:influenced
|
gptkb:Interpretability_Tools
gptkb:Mechanistic_Interpretability_Community
AI Alignment Research
|
|
gptkbp:influencedBy
|
gptkb:Feature_Visualization_in_CNNs
gptkb:DeepDream
Neuroscience
|
|
gptkbp:language
|
English
|
|
gptkbp:method
|
gptkb:Activation_Patching
Ablation Studies
Circuit Decomposition
Feature Attribution
Visualization of Weights
|
|
gptkbp:notableContributor
|
gptkb:Nick_Schiefer
gptkb:Gabriel_Goh
gptkb:Shan_Carter
gptkb:Catherine_Olsson
gptkb:Chris_Olah
gptkb:Nelson_Elhage
gptkb:Tom_Henighan
gptkb:Ludwig_Schubert
|
|
gptkbp:notableFinds
|
gptkb:Induction_Heads_in_Transformers
Algorithmic Circuits in Language Models
Modularity in Transformer Layers
Superposition of Features
|
|
gptkbp:notablePublication
|
gptkb:Transformer_Circuits_Thread
gptkb:A_Mathematical_Framework_for_Transformer_Circuits
|
|
gptkbp:relatedConcept
|
gptkb:Attention_Heads
gptkb:Induction_Heads
gptkb:Language_Models
gptkb:MLP_Neurons
gptkb:Mechanistic_Interpretability
gptkb:GPT-2
gptkb:Feature_Visualization
gptkb:BERT
Circuit Analysis
Superposition in Neural Networks
|
|
gptkbp:startDate
|
2021
|
|
gptkbp:website
|
https://transformer-circuits.pub
|
|
gptkbp:bfsParent
|
gptkb:Neel_Nanda
|
|
gptkbp:bfsLayer
|
7
|