© 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 EvalsExportsinterp-engineNEWAPI 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. 4191
    Prev
    Next
    INDEX
    Explanations

    specific time indicators followed by event descriptions

    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
    239
    +0.11
    0.5%
    80
    +0.11
    0.5%
    721
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    495
    +0.11
    0.04
    239
    +0.11
    0.03
    401
    +0.10
    0.03
    Negative Logits
    enhagen
    -0.70
    ittens
    -0.68
    schild
    -0.68
    ouver
    -0.68
    roups
    -0.66
    lines
    -0.65
    estation
    -0.64
    ulkan
    -0.63
    gew
    -0.62
    organ
    -0.62
    POSITIVE LOGITS
    fter
    0.75
    GHz
    0.72
     GHz
    0.71
     Nieto
    0.70
    thood
    0.69
    mares
    0.67
    ©¶æ
    0.66
     Centauri
    0.65
    omial
    0.64
     increments
    0.62
    Activations Density 0.090%

    No Known Activations