© 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. 8739
    Prev
    Next
    INDEX
    Explanations

    the word "lock" or words related to security or control

    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
    189
    +0.13
    0.6%
    0
    +0.11
    0.5%
    326
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    189
    +0.13
    0.02
    326
    +0.11
    0.01
    32
    +0.10
    0.02
    Negative Logits
    issance
    -0.87
    LV
    -0.78
    schild
    -0.73
    ãĤ¡
    -0.71
    enegger
    -0.70
    abama
    -0.69
    ilater
    -0.68
    olf
    -0.66
    xual
    -0.66
    resso
    -0.66
    POSITIVE LOGITS
    picking
    1.25
    heed
    1.17
    pick
    1.09
    creen
    1.06
    door
    1.02
    step
    0.96
    lear
    0.94
    hold
    0.92
    downs
    0.91
     horns
    0.87
    Activations Density 0.028%

    No Known Activations