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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 3072
    5. 8-RES_FS3072-JB
    6. 1406
    Prev
    Next
    INDEX
    Explanations

    references to locations and events related to the Bundy family and the Las Vegas area

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    649
    +0.13
    0.6%
    383
    +0.13
    0.6%
    288
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.14
    659
    +0.13
    0.09
    326
    +0.13
    0.09
    Negative Logits
    hops
    -0.76
    urized
    -0.71
    hole
    -0.70
    ulate
    -0.69
    ui
    -0.65
    Oracle
    -0.64
    upp
    -0.63
    odan
    -0.63
     artif
    -0.62
    ible
    -0.61
    POSITIVE LOGITS
    zman
    0.93
     Springs
    0.89
    ertodd
    0.84
     Coyotes
    0.84
    agne
    0.81
     Vegas
    0.79
    eers
    0.78
    eting
    0.76
    agna
    0.74
     Alto
    0.74
    Activations Density 1.406%

    No Known Activations