© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 22435
    Prev
    Next
    INDEX
    Explanations

    commands or steps related to setting up and running an application

    oai_token-act-pair · gpt-3.5-turbo

    keywords related to programming, specifically commands and functionalities associated with application development and package management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Letter
    -0.72
     Lia
    -0.71
     Pai
    -0.71
     Fei
    -0.71
     Hilton
    -0.70
    MSN
    -0.70
     Payne
    -0.68
    Crime
    -0.68
    incerity
    -0.68
     Northwestern
    -0.67
    POSITIVE LOGITS
     docker
    1.57
     Docker
    1.47
     dependencies
    1.47
     npm
    1.38
    docker
    1.26
     dependency
    1.23
     cabal
    1.22
     Jenkins
    1.16
     install
    1.16
     build
    1.15
    Activations Density 0.208%

    No Known Activations