© 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. 13068
    Prev
    Next
    INDEX
    Explanations

    words related to employment, work, and workforce

    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
    459
    +0.13
    0.6%
    614
    +0.10
    0.4%
    542
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    737
    +0.13
    0.04
    455
    +0.10
    0.04
    542
    +0.09
    0.04
    Negative Logits
    oneliness
    -0.80
    İĭ
    -0.79
    cffff
    -0.74
    ancies
    -0.71
    atomic
    -0.67
    sleep
    -0.65
    erved
    -0.64
    Å¡
    -0.64
    thinkable
    -0.62
    algia
    -0.62
    POSITIVE LOGITS
     contributing
    0.77
     determining
    0.76
     confronting
    0.73
     thereof
    0.71
     underpin
    0.71
     shaping
    0.71
     behind
    0.70
     indu
    0.69
     contributors
    0.69
     motivating
    0.68
    Activations Density 0.167%

    No Known Activations