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. 23757
    Prev
    Next
    INDEX
    Explanations

    the letter 's' in the text

    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
    447
    +0.27
    1.3%
    480
    +0.26
    1.3%
    87
    +0.15
    0.8%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    464
    +0.27
    0.03
    31
    +0.26
    0.03
    134
    +0.15
    0.03
    Negative Logits
     Niet
    -0.65
     respons
    -0.64
     Mellon
    -0.62
     Borders
    -0.60
     Pulitzer
    -0.59
     occas
    -0.59
     CPR
    -0.58
     colleg
    -0.57
     Nev
    -0.57
     Staples
    -0.56
    POSITIVE LOGITS
    maxwell
    0.83
    ip
    0.80
    _
    0.75
    Ther
    0.75
    jac
    0.75
    xc
    0.75
    fc
    0.75
    vm
    0.75
    mb
    0.73
    john
    0.73
    Activations Density 0.075%

    No Known Activations