© 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. 14475
    Prev
    Next
    INDEX
    Explanations

    words related to continuous actions or states

    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
    301
    +0.12
    0.6%
    481
    +0.10
    0.4%
    9
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    404
    +0.12
    0.03
    222
    +0.10
    0.02
    151
    +0.09
    0.03
    Negative Logits
    imore
    -0.85
    eport
    -0.80
    ington
    -0.77
    udeb
    -0.77
    ovember
    -0.77
    roups
    -0.75
    kees
    -0.75
    weeney
    -0.75
    yp
    -0.73
    neau
    -0.73
    POSITIVE LOGITS
     vigilance
    0.99
     devotion
    0.92
     admiration
    0.84
     optimism
    0.83
     sunshine
    0.82
     gratitude
    0.82
     loyalty
    0.80
     passion
    0.79
     gravitational
    0.79
     allegiance
    0.79
    Activations Density 0.100%

    No Known Activations