© 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. 12316
    Prev
    Next
    INDEX
    Explanations

    mentions of people being alive or deceased

    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
    132
    +0.14
    0.6%
    270
    +0.10
    0.5%
    223
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    132
    +0.14
    0.02
    513
    +0.10
    0.01
    223
    +0.10
    0.01
    Negative Logits
    RECT
    -0.71
    soDeliveryDate
    -0.65
     Aerospace
    -0.65
    ãĥĩ
    -0.62
    cipl
    -0.62
    addy
    -0.61
    ple
    -0.60
    ciples
    -0.59
    liga
    -0.59
    é¾įå
    -0.59
    POSITIVE LOGITS
    lihood
    1.05
    abouts
    0.92
     alive
    0.81
    lier
    0.80
    terday
    0.77
    beat
    0.73
    nces
    0.72
    itable
    0.70
    mares
    0.70
    weight
    0.70
    Activations Density 0.023%

    No Known Activations