© 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. 4006
    Prev
    Next
    INDEX
    Explanations

    statements related to investigations and critical evaluations of organizations or individuals

    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
    87
    +0.18
    0.9%
    373
    +0.09
    0.4%
    497
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    408
    +0.18
    0.06
    195
    +0.09
    0.02
    748
    +0.08
    0.02
    Negative Logits
    soever
    -0.74
    ña
    -0.63
     WRITE
    -0.61
    apist
    -0.59
    imaru
    -0.58
    iva
    -0.57
    advertising
    -0.56
     Cups
    -0.55
    §
    -0.55
    Handle
    -0.55
    POSITIVE LOGITS
     similarities
    1.15
     discrepancies
    1.13
     inconsistencies
    1.06
     shortcomings
    1.01
     misconceptions
    1.00
     differences
    0.99
     inaccur
    0.97
     firsthand
    0.96
     disparities
    0.95
     hypocrisy
    0.93
    Activations Density 0.510%

    No Known Activations