© 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 · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 7728
    Prev
    Next
    INDEX
    Explanations

    the name "Luis" in various contexts

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    238
    +0.14
    0.7%
    430
    +0.11
    0.5%
    504
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.14
    0.01
    610
    +0.11
    0.01
    316
    +0.10
    0.01
    Negative Logits
    ulhu
    -0.78
    BOOK
    -0.76
    orph
    -0.72
    urbed
    -0.72
    Ĥª
    -0.70
    Ħ¢
    -0.70
    ¥µ
    -0.69
    ritic
    -0.69
    opian
    -0.68
    ebook
    -0.68
    POSITIVE LOGITS
     Enrique
    1.23
     Suarez
    1.14
     Luis
    1.00
     Carlos
    0.94
     Alberto
    0.92
     Gomez
    0.91
     Fernando
    0.91
     Santos
    0.89
     Rivera
    0.86
     Gustav
    0.85
    Activations Density 0.014%

    No Known Activations