© 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. 25958
    Prev
    Next
    INDEX
    Explanations

    HTML tags and related syntax in the text

    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
    653
    +0.11
    0.5%
    314
    +0.11
    0.5%
    359
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    653
    +0.11
    0.02
    160
    +0.11
    0.02
    358
    +0.10
    0.01
    Negative Logits
    ãĥ£
    -0.80
     Reborn
    -0.77
    ModLoader
    -0.77
     Ferr
    -0.67
     bitters
    -0.66
     exerc
    -0.66
     Sapphire
    -0.64
     virginity
    -0.64
     derog
    -0.64
     Winchester
    -0.63
    POSITIVE LOGITS
    !--
    1.33
    img
    1.18
    span
    1.12
    iframe
    1.08
    div
    1.04
    meta
    0.95
    html
    0.95
    story
    0.84
    ><
    0.84
    br
    0.82
    Activations Density 0.008%

    No Known Activations