© 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. 20740
    Prev
    Next
    INDEX
    Explanations

    questions or statements that present a contrast or raise doubt

    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
    739
    +0.09
    0.4%
    460
    +0.09
    0.4%
    512
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    512
    +0.09
    0.04
    170
    +0.09
    0.04
    507
    +0.09
    0.04
    Negative Logits
    throp
    -0.90
    eor
    -0.70
    vae
    -0.62
    clude
    -0.62
    opted
    -0.62
     faiths
    -0.61
    rup
    -0.61
     Particip
    -0.61
    gian
    -0.61
     derog
    -0.60
    POSITIVE LOGITS
     not
    0.84
     indeed
    0.80
     NOT
    0.79
     compounded
    0.78
     undoubtedly
    0.78
     whether
    0.76
     still
    0.74
     squarely
    0.74
     ALWAYS
    0.73
     therefore
    0.72
    Activations Density 0.108%

    No Known Activations