© 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. 4890
    Prev
    Next
    INDEX
    Explanations

    descriptions related to underwater movement and technology, and capabilities of specific vehicles such as submarines and drones

    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
    678
    +0.14
    0.6%
    664
    +0.10
    0.5%
    418
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.14
    0.05
    570
    +0.10
    0.02
    252
    +0.10
    0.04
    Negative Logits
    Theme
    -0.83
    Developer
    -0.77
    displayText
    -0.75
     precaution
    -0.72
     Practices
    -0.72
    çīĪ
    -0.70
    Fund
    -0.70
    Spons
    -0.69
    Particip
    -0.68
    Acknowled
    -0.68
    POSITIVE LOGITS
     efficiently
    1.07
     effortlessly
    0.99
     underwater
    0.96
     safely
    0.96
     reliably
    0.96
     speeds
    0.94
     distances
    0.92
     indefinitely
    0.89
     easily
    0.85
     withstand
    0.85
    Activations Density 0.499%

    No Known Activations