© 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. 17450
    Prev
    Next
    INDEX
    Explanations

    the name "Donovan"

    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
    447
    +0.21
    1.0%
    718
    +0.12
    0.6%
    99
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.21
    0.03
    288
    +0.12
    0.04
    326
    +0.11
    0.03
    Negative Logits
    phrine
    -0.84
    ration
    -0.81
    lasses
    -0.79
    erate
    -0.78
    sed
    -0.77
    tarian
    -0.77
    Ń
    -0.77
    tics
    -0.74
    scenes
    -0.72
    ccording
    -0.71
    POSITIVE LOGITS
     Vale
    0.66
     Bee
    0.64
    iso
    0.63
     Sz
    0.62
     Cros
    0.61
     Lap
    0.60
     Carter
    0.60
     Marcos
    0.59
     Episcopal
    0.59
     Jem
    0.59
    Activations Density 0.084%

    No Known Activations