© 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. 1-RES-JB
    11. 23215
    Prev
    Next
    INDEX
    Explanations

    words related to American football, specifically the position of quarterback

    oai_token-act-pair · gpt-3.5-turbo

    references to quarterbacks in football contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erville
    -0.77
     Debor
    -0.71
    cling
    -0.71
    hips
    -0.68
     Barcl
    -0.68
     actionGroup
    -0.68
    orporated
    -0.68
     Sturgeon
    -0.67
    henko
    -0.65
     EntityItem
    -0.65
    POSITIVE LOGITS
    QB
    0.98
     QB
    0.92
    PF
    0.87
    MJ
    0.79
    TF
    0.77
    JJ
    0.74
    TI
    0.72
    KK
    0.68
    OF
    0.68
    books
    0.67
    Activations Density 0.004%

    No Known Activations