© 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. 11-RES-JB
    11. 20953
    Prev
    Next
    INDEX
    Explanations

    names of sports teams and players along with their career statistics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of teams and players' career timelines in sports contexts

    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
     tomorrow
    -0.69
    morrow
    -0.66
    atum
    -0.60
    itely
    -0.58
    cific
    -0.55
    orders
    -0.54
     asymm
    -0.54
     quarterly
    -0.54
    aiman
    -0.53
    omever
    -0.53
    POSITIVE LOGITS
     before
    0.85
     stint
    0.78
    before
    0.72
    Playing
    0.70
     earning
    0.68
     ().
    0.66
     fame
    0.65
    dating
    0.65
     culminating
    0.63
     averaging
    0.62
    Activations Density 0.544%

    No Known Activations