© 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. 3058
    Prev
    Next
    INDEX
    Explanations

    email addresses in text

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    132
    +0.12
    0.5%
    319
    +0.10
    0.5%
    258
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    319
    +0.12
    0.04
    132
    +0.10
    0.04
    258
    +0.10
    0.04
    Negative Logits
    liga
    -0.80
    TRY
    -0.78
    jury
    -0.72
     Templar
    -0.68
     Vanderbilt
    -0.67
    antle
    -0.67
    anu
    -0.66
    ICLE
    -0.64
    Jer
    -0.62
     Statue
    -0.62
    POSITIVE LOGITS
     inbox
    1.23
     address
    1.15
     correspondence
    1.10
     addresses
    1.09
    address
    1.01
     newsletters
    0.98
     messages
    0.94
     Address
    0.93
    boxes
    0.90
     communications
    0.90
    Activations Density 0.038%

    No Known Activations