© 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. 15899
    Prev
    Next
    INDEX
    Explanations

    words related to chaos and disorder

    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
    480
    +0.58
    3.2%
    266
    +0.12
    0.7%
    4
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.58
    0.02
    266
    +0.12
    0.10
    608
    +0.09
    0.08
    Negative Logits
     guiName
    -0.66
     Historically
    -0.65
    quartered
    -0.60
    inav
    -0.59
    hovah
    -0.58
     intrinsically
    -0.57
     inherently
    -0.57
    yip
    -0.56
    htaking
    -0.56
     interacts
    -0.53
    POSITIVE LOGITS
     relent
    0.71
     thereafter
    0.68
     promptly
    0.64
     hurried
    0.59
     ensued
    0.58
     reluctantly
    0.58
     afterward
    0.57
    Later
    0.56
     refund
    0.56
     rejo
    0.56
    Activations Density 1.315%

    No Known Activations