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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 10-RES-JB
    11. 19075
    Prev
    Next
    INDEX
    Explanations

    references to "The Simpsons" and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to "The Simpsons" and locations associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lance
    -0.80
    atform
    -0.73
    aphael
    -0.71
    asta
    -0.70
    apter
    -0.69
    board
    -0.67
     Chocobo
    -0.65
     Shades
    -0.65
    aird
    -0.64
    riors
    -0.64
    POSITIVE LOGITS
     Simpson
    0.99
    ãħĭ
    0.73
    ocene
    0.71
    ãħĭãħĭ
    0.69
    enegger
    0.67
     Farms
    0.65
    âĶģ
    0.64
     Tigers
    0.62
    æĸ¹
    0.61
     eru
    0.60
    Activations Density 0.093%

    No Known Activations