© 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. 3023
    Prev
    Next
    INDEX
    Explanations

    references to physical media formats like Blu-ray and DVD releases

    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
    481
    +0.17
    0.8%
    457
    +0.12
    0.6%
    464
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.17
    0.03
    464
    +0.12
    0.03
    475
    +0.12
    0.02
    Negative Logits
    onomous
    -0.97
    ndra
    -0.96
    astical
    -0.95
    maxwell
    -0.77
    aido
    -0.73
    hap
    -0.73
    inic
    -0.72
    eric
    -0.71
    pid
    -0.71
    nel
    -0.71
    POSITIVE LOGITS
     DVD
    1.14
     editions
    1.01
     DVDs
    1.00
     copies
    0.99
     formats
    0.96
     playback
    0.95
     edition
    0.95
     discs
    0.95
    DVD
    0.94
     cassette
    0.94
    Activations Density 0.133%

    No Known Activations