© 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. 15345
    Prev
    Next
    INDEX
    Explanations

    statements or phrases with the word "beg" or its variations

    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
    526
    +0.12
    0.5%
    178
    +0.10
    0.5%
    695
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    526
    +0.12
    0.01
    695
    +0.10
    0.01
    750
    +0.09
    0.01
    Negative Logits
    ulty
    -0.73
     Democr
    -0.66
     Cheong
    -0.66
    visors
    -0.63
    ership
    -0.63
    iance
    -0.63
    jiang
    -0.63
    iership
    -0.62
     Ion
    -0.62
     Scope
    -0.62
    POSITIVE LOGITS
     pardon
    1.05
    otten
    1.03
     forgiveness
    1.02
     begging
    0.79
    ingly
    0.78
    onia
    0.76
    FontSize
    0.74
    anke
    0.73
    hammad
    0.72
    haps
    0.72
    Activations Density 0.023%

    No Known Activations