© 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 49152
    9. 8-RES_FS49152-JB
    11. 25996
    Prev
    Next
    INDEX
    Explanations

    instances of the word "declare" and its variations in different contexts, indicating a focus on declarations or formal statements

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    92
    +0.12
    0.6%
    642
    +0.10
    0.4%
    53
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    53
    +0.12
    0.02
    92
    +0.10
    0.02
    100
    +0.09
    0.02
    Negative Logits
    RH
    -0.75
    Rh
    -0.70
    dayName
    -0.67
    isoft
    -0.67
    alez
    -0.65
    anuts
    -0.64
    engers
    -0.63
    pps
    -0.63
    umbn
    -0.63
    Reply
    -0.62
    POSITIVE LOGITS
     bankruptcy
    1.08
    phas
    0.97
     allegiance
    0.92
     unequivocally
    0.86
     victory
    0.85
     independence
    0.82
     aloud
    0.80
     martial
    0.79
     war
    0.79
     moratorium
    0.77
    Activations Density 0.017%

    No Known Activations