© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 19606
    Prev
    Next
    INDEX
    Explanations

    email-related content

    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
    395
    +0.09
    0.4%
    678
    +0.09
    0.4%
    697
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.09
    0.01
    194
    +0.09
    0.01
    755
    +0.08
    0.01
    Negative Logits
     Shack
    -0.62
    Phill
    -0.59
     Episcopal
    -0.58
     Ath
    -0.58
     Hood
    -0.56
    Gall
    -0.56
     dracon
    -0.55
     hog
    -0.55
    lessness
    -0.54
    uthor
    -0.54
    POSITIVE LOGITS
    interstitial
    0.96
    email
    0.78
    ento
    0.74
    pload
    0.71
    arez
    0.70
    olicited
    0.70
     newsletter
    0.69
     newsletters
    0.69
     externalToEVAOnly
    0.68
    essage
    0.68
    Activations Density 0.015%

    No Known Activations