© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19460
    Prev
    Next
    INDEX
    Explanations

    the name "Mary."

    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
    35
    +0.10
    0.5%
    459
    +0.10
    0.5%
    377
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    141
    +0.10
    0.02
    758
    +0.10
    0.02
    628
    +0.10
    0.02
    Negative Logits
    itars
    -0.82
    */(
    -0.80
    cffff
    -0.76
    sequence
    -0.74
    ickr
    -0.72
    asio
    -0.69
    fty
    -0.69
    oldemort
    -0.69
    herer
    -0.68
    ierrez
    -0.67
    POSITIVE LOGITS
    lene
    1.11
     Jane
    0.98
    anne
    0.96
    mount
    0.95
    anna
    0.93
    Kay
    0.92
     Beth
    0.91
    Anne
    0.90
     Sue
    0.88
     Louise
    0.88
    Activations Density 0.017%

    No Known Activations