© 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 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. 7-RES-JB
    11. 24052
    Prev
    Next
    INDEX
    Explanations

    mentions of sports events taking place at home venues

    oai_token-act-pair · gpt-3.5-turbo

    references to home games in sports contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifter
    -0.77
    enegger
    -0.74
    ascript
    -0.72
    asus
    -0.71
    oola
    -0.71
    uality
    -0.67
    opian
    -0.67
    ppe
    -0.66
    abus
    -0.64
    olini
    -0.64
    POSITIVE LOGITS
    grown
    0.89
     opener
    0.84
     rivalry
    0.84
     teammate
    0.83
     games
    0.81
     playoff
    0.80
     stadium
    0.79
     ballpark
    0.78
    coming
    0.78
     rink
    0.77
    Activations Density 0.046%

    No Known Activations