© 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. 14544
    Prev
    Next
    INDEX
    Explanations

    phrases related to ongoing or continuous actions

    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
    481
    +0.16
    0.8%
    282
    +0.09
    0.4%
    61
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    282
    +0.16
    0.05
    703
    +0.09
    0.04
    300
    +0.09
    0.05
    Negative Logits
    isks
    -0.67
    dds
    -0.67
    hatt
    -0.61
    chet
    -0.60
    ereo
    -0.58
    Surv
    -0.58
    ainers
    -0.58
    atin
    -0.57
    ced
    -0.57
    nis
    -0.57
    POSITIVE LOGITS
     incidentally
    1.01
     respectively
    0.79
     admittedly
    0.75
     notoriously
    0.72
     jointly
    0.72
     prominently
    0.71
     essentially
    0.70
     ironically
    0.69
     hereafter
    0.69
     largely
    0.69
    Activations Density 0.384%

    No Known Activations