© 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. 8623
    Prev
    Next
    INDEX
    Explanations

    information related to statistics and percentages in text

    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
    227
    +0.11
    0.5%
    459
    +0.11
    0.5%
    124
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    223
    +0.11
    0.05
    227
    +0.11
    0.03
    260
    +0.10
    0.04
    Negative Logits
    assetsadobe
    -0.81
    prep
    -0.63
     Purchase
    -0.61
    busters
    -0.60
     dx
    -0.57
    rake
    -0.56
    Draft
    -0.56
    Hack
    -0.55
     Zionism
    -0.55
     Timeline
    -0.55
    POSITIVE LOGITS
    ½
    0.84
     fewer
    0.77
     teasp
    0.76
    fort
    0.75
    thur
    0.73
     ½
    0.73
    osponsors
    0.71
    thirds
    0.70
     thereafter
    0.70
     additional
    0.70
    Activations Density 0.140%

    No Known Activations