© 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. 6-RES-JB
    11. 978
    Prev
    Next
    INDEX
    Explanations

    names related to various sports teams

    oai_token-act-pair · gpt-3.5-turbo

    names of sports teams, particularly football clubs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NetMessage
    -0.82
    iframe
    -0.76
    VALUE
    -0.76
    rez
    -0.73
    GMT
    -0.72
    ãĥ¼ãĤ¯
    -0.71
     Adin
    -0.71
     Zup
    -0.70
    selection
    -0.68
    ãĥ´
    -0.68
    POSITIVE LOGITS
    wich
    0.96
    pton
    0.84
     Athletic
    0.81
     Express
    0.79
     Networks
    0.72
    shire
    0.71
    mere
    0.69
     Racing
    0.69
     Athletics
    0.68
     Radio
    0.67
    Activations Density 0.048%

    No Known Activations