© 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. 22360
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "for."

    oai_token-act-pair · gpt-4o-miniTriggered 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
    608
    +0.14
    0.6%
    362
    +0.11
    0.5%
    572
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.14
    0.04
    609
    +0.11
    0.03
    362
    +0.11
    0.03
    Negative Logits
    deen
    -0.78
     Accessed
    -0.78
    ipple
    -0.74
    chenko
    -0.74
    Force
    -0.72
    nex
    -0.72
    loo
    -0.69
    LM
    -0.69
    naire
    -0.67
    amed
    -0.67
    POSITIVE LOGITS
    geries
    0.90
     optimum
    0.85
     occupancy
    0.83
     anything
    0.82
     experimentation
    0.81
     comparison
    0.81
     purposes
    0.80
     takeoff
    0.78
     optimal
    0.77
     inclusion
    0.77
    Activations Density 0.100%

    No Known Activations