© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 16895
    Prev
    Next
    INDEX
    Explanations

    in-depth information related to sports events and game schedules

    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
    430
    +0.17
    0.8%
    640
    +0.15
    0.7%
    447
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.17
    0.12
    430
    +0.15
    0.10
    640
    +0.14
    0.09
    Negative Logits
     involuntary
    -0.89
     implants
    -0.82
     neglig
    -0.81
     biological
    -0.81
     manuals
    -0.78
     prototyp
    -0.77
     unus
    -0.77
     manual
    -0.77
     untreated
    -0.77
     coerc
    -0.77
    POSITIVE LOGITS
     Featuring
    1.42
     Tickets
    1.36
     Congratulations
    1.28
     Located
    1.27
    Tickets
    1.22
     Tonight
    1.20
     Dates
    1.17
     Fans
    1.17
     Yesterday
    1.16
     Guests
    1.14
    Activations Density 0.397%

    No Known Activations