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. 23569
    Prev
    Next
    INDEX
    Explanations

    references to the name "Mickey."

    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
    161
    +0.11
    0.5%
    350
    +0.10
    0.5%
    121
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.03
    161
    +0.10
    0.03
    326
    +0.09
    0.02
    Negative Logits
    iance
    -1.03
    iminary
    -0.95
    iar
    -0.93
    lain
    -0.92
    minist
    -0.90
    inas
    -0.90
    adem
    -0.89
    icum
    -0.87
    esian
    -0.86
    iant
    -0.86
    POSITIVE LOGITS
     Mouse
    1.17
     Hayes
    1.03
     Rogers
    1.01
     Romero
    0.98
     Mae
    0.95
     Martinez
    0.89
     Lomb
    0.89
     Pie
    0.89
     Nichols
    0.88
     Robinson
    0.87
    Activations Density 0.074%

    No Known Activations