© 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 EvalsExportsAPI 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. 12202
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer programming and software development

    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
    640
    +0.25
    1.2%
    373
    +0.17
    0.8%
    116
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.25
    0.09
    328
    +0.17
    0.04
    615
    +0.09
    0.04
    Negative Logits
    tsky
    -0.78
    ername
    -0.74
    xual
    -0.62
     inward
    -0.57
    hement
    -0.57
     WRITE
    -0.54
     ital
    -0.54
    ighth
    -0.53
    quin
    -0.53
     brunt
    -0.52
    POSITIVE LOGITS
    ammy
    0.71
    Premium
    0.64
     Allows
    0.64
     Proced
    0.61
    rentice
    0.61
    earances
    0.61
    Slot
    0.61
    unch
    0.60
    Synopsis
    0.59
     Airl
    0.59
    Activations Density 0.170%

    No Known Activations