Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23844
    Prev
    Next
    INDEX
    Explanations

    mentions of sports franchises and their historical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    288
    +0.16
    0.7%
    583
    +0.12
    0.6%
    566
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.16
    0.01
    652
    +0.12
    0.01
    583
    +0.12
    0.01
    Negative Logits
    ynthesis
    -0.80
    board
    -0.78
    boards
    -0.74
    hran
    -0.70
    izoph
    -0.67
     Thou
    -0.66
    Downloadha
    -0.66
    mith
    -0.66
    afa
    -0.64
    ennett
    -0.64
    POSITIVE LOGITS
    eers
    0.99
    atical
    0.84
     cornerstone
    0.77
     mascot
    0.76
    rats
    0.75
     franchise
    0.73
    ational
    0.72
    atics
    0.71
    atile
    0.71
    arily
    0.71
    Activations Density 0.019%

    No Known Activations