© 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. 18979
    Prev
    Next
    INDEX
    Explanations

    soccer-related terms and mentions of specific soccer clubs

    oai_token-act-pair · gpt-3.5-turbo

    references to sports clubs and their activities

    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
    aminer
    -0.80
    Wikipedia
    -0.78
    isSpecialOrderable
    -0.78
     Whedon
    -0.73
     Pamela
    -0.72
    Larry
    -0.69
     Whitney
    -0.68
    TED
    -0.67
    berman
    -0.67
    abbage
    -0.65
    POSITIVE LOGITS
     FC
    1.26
     Athletic
    1.24
     midfielder
    1.14
     goalkeeper
    1.13
     relegation
    1.10
     striker
    1.07
     Juventus
    1.01
     ultras
    1.00
     Stadium
    0.98
     Marse
    0.97
    Activations Density 0.182%

    No Known Activations