© 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. 18523
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and statistics, particularly focusing on points scored and rebounds in basketball games

    oai_token-act-pair · gpt-3.5-turbo

    statistical data related to sports performance metrics

    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
    catentry
    -0.68
    argon
    -0.65
    bryce
    -0.63
    llah
    -0.62
     Sorce
    -0.61
     skelet
    -0.59
    ctl
    -0.58
    details
    -0.56
    Ü
    -0.56
    geist
    -0.56
    POSITIVE LOGITS
     apiece
    1.36
     totaling
    0.92
     against
    0.88
    against
    0.87
    ugi
    0.79
     Saturday
    0.78
     midway
    0.78
     vs
    0.77
    plus
    0.77
     versus
    0.77
    Activations Density 0.087%

    No Known Activations