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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18398
    Prev
    Next
    INDEX
    Explanations

    information about physical dimensions, specifically measurements (e.g., inches) with specific values

    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
    407
    +0.11
    0.5%
    657
    +0.10
    0.5%
    529
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.11
    0.01
    469
    +0.10
    0.01
    518
    +0.10
    0.02
    Negative Logits
    ocy
    -0.80
    wart
    -0.74
    aden
    -0.73
    sequence
    -0.71
    anim
    -0.69
    warts
    -0.68
    yrinth
    -0.68
    ciplinary
    -0.67
    tower
    -0.67
    Hor
    -0.66
    POSITIVE LOGITS
     $
    1.77
     ¥
    1.64
     £
    1.60
     âĤ¬
    1.52
     Rs
    1.42
    $
    1.32
     "$
    1.27
    =$
    1.23
     $(
    1.18
     $$
    1.18
    Activations Density 0.061%

    No Known Activations