© 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. 4990
    Prev
    Next
    INDEX
    Explanations

    instances where a comparison is made regarding timeframes or events happening simultaneously

    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
    715
    +0.10
    0.4%
    215
    +0.10
    0.4%
    183
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    183
    +0.10
    0.02
    671
    +0.10
    0.02
    715
    +0.09
    0.02
    Negative Logits
    Pacific
    -0.81
     Flavoring
    -0.73
    ר
    -0.72
    vantage
    -0.70
    asus
    -0.70
    externalActionCode
    -0.69
    âĸij
    -0.69
    Commerce
    -0.69
    ¨
    -0.69
    ESS
    -0.68
    POSITIVE LOGITS
     accounting
    0.80
     disclaim
    0.74
     watered
    0.72
     exhaustive
    0.71
     diminishing
    0.68
     technically
    0.67
     caveats
    0.67
     slight
    0.67
     declining
    0.67
     adjusting
    0.65
    Activations Density 0.038%

    No Known Activations