© 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. 5479
    Prev
    Next
    INDEX
    Explanations

    mentions of current events and political figures

    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
    314
    +0.18
    0.8%
    616
    +0.12
    0.6%
    640
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    123
    +0.18
    0.06
    22
    +0.12
    0.06
    322
    +0.11
    0.05
    Negative Logits
     alloc
    -0.68
    uces
    -0.64
    Voice
    -0.62
    irl
    -0.60
    CRIPTION
    -0.59
     intimid
    -0.59
     ethic
    -0.57
     Sorceress
    -0.56
     rapists
    -0.56
    NOW
    -0.54
    POSITIVE LOGITS
    escap
    1.19
    ching
    1.17
    bred
    1.05
    operative
    1.04
     jeopardy
    1.02
    strument
    1.00
    patient
    1.00
    humane
    0.99
    ordinate
    0.95
    itialized
    0.95
    Activations Density 0.119%

    No Known Activations