© 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. 4-RES-JB
    11. 7348
    Prev
    Next
    INDEX
    Explanations

    keywords related to the Python web framework Django

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Django framework

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iating
    -0.70
    NetMessage
    -0.70
    ament
    -0.67
    ICLE
    -0.65
    hem
    -0.65
     Bris
    -0.65
    ELY
    -0.65
    creen
    -0.64
    entimes
    -0.64
    ships
    -0.62
    POSITIVE LOGITS
     Django
    1.33
     Unch
    1.02
     Flask
    0.93
    ango
    0.82
     dj
    0.73
    geist
    0.71
    quez
    0.69
    Daddy
    0.69
    cember
    0.68
     flask
    0.68
    Activations Density 0.014%

    No Known Activations