© 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. 3952
    Prev
    Next
    INDEX
    Explanations

    expressions of opinions or sentiments in written text

    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
    760
    +0.11
    0.5%
    612
    +0.09
    0.4%
    548
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    195
    +0.11
    0.03
    760
    +0.09
    0.04
    729
    +0.09
    0.04
    Negative Logits
     ILCS
    -0.73
     Located
    -0.66
     Created
    -0.66
     Photograph
    -0.64
     Printing
    -0.63
    Skip
    -0.58
    Course
    -0.58
     CrossRef
    -0.58
    cko
    -0.57
     Maintenance
    -0.56
    POSITIVE LOGITS
     sarcast
    0.96
     succinct
    0.89
     scathing
    0.88
     clar
    0.87
     remarks
    0.85
     upbeat
    0.85
     acknow
    0.84
    rompt
    0.83
     emphatically
    0.83
     explaining
    0.83
    Activations Density 0.416%

    No Known Activations