© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 4024
    Prev
    Next
    INDEX
    Explanations

    words related to footwear, particularly shoes

    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
    592
    +0.13
    0.6%
    464
    +0.11
    0.5%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.01
    592
    +0.11
    0.02
    343
    +0.11
    0.02
    Negative Logits
    enance
    -0.83
    REDACTED
    -0.75
    erest
    -0.71
    ancial
    -0.70
    yrinth
    -0.70
    PsyNetMessage
    -0.70
    itative
    -0.69
    iversal
    -0.67
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.66
    iov
    -0.65
    POSITIVE LOGITS
    toe
    1.05
     shoes
    1.03
    prints
    1.01
    horn
    1.00
    pee
    0.96
     Shoes
    0.94
     worn
    0.92
     footwear
    0.89
     heel
    0.89
     shoe
    0.84
    Activations Density 0.034%

    No Known Activations