© 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. 20631
    Prev
    Next
    INDEX
    Explanations

    phrases indicating strong emphasis or importance

    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
    295
    +0.11
    0.5%
    523
    +0.10
    0.4%
    75
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    298
    +0.11
    0.03
    523
    +0.10
    0.03
    736
    +0.09
    0.03
    Negative Logits
    ntil
    -0.99
    ©¶æ
    -0.74
    iliation
    -0.74
    doctor
    -0.72
    iliate
    -0.71
    bley
    -0.71
     Murd
    -0.71
    ertodd
    -0.70
    achus
    -0.69
    eton
    -0.68
    POSITIVE LOGITS
     amazing
    0.72
    ities
    0.70
    liness
    0.70
     wonderful
    0.69
     mundane
    0.69
     phenomenal
    0.69
     incredible
    0.69
     exquisite
    0.69
    worldly
    0.67
     marvelous
    0.67
    Activations Density 0.039%

    No Known Activations