© 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. 26010
    Prev
    Next
    INDEX
    Explanations

    names of characters or figures, particularly those associated with notable actions or events

    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
    728
    +0.12
    0.6%
    491
    +0.11
    0.5%
    57
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.01
    99
    +0.11
    0.01
    326
    +0.11
    0.01
    Negative Logits
    aging
    -1.11
    sburgh
    -0.97
    ding
    -0.92
    aged
    -0.92
    ship
    -0.89
    spr
    -0.87
    drivers
    -0.86
    agers
    -0.85
    wall
    -0.84
    ning
    -0.84
    POSITIVE LOGITS
     Hawking
    0.80
    xual
    0.79
     Leth
    0.77
     Georg
    0.74
     Den
    0.73
     Vict
    0.72
    ;;;;;;;;;;;;
    0.71
     Voters
    0.70
     Gentleman
    0.69
     Dynam
    0.69
    Activations Density 0.008%

    No Known Activations