© 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. 20977
    Prev
    Next
    INDEX
    Explanations

    ingredients often used in cooking or baking recipes, such as specific food items or cooking techniques

    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
    524
    +0.11
    0.5%
    564
    +0.11
    0.5%
    245
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    564
    +0.11
    0.04
    304
    +0.11
    0.04
    444
    +0.10
    0.03
    Negative Logits
    eatures
    -0.78
     partName
    -0.77
     HIT
    -0.75
    lisher
    -0.72
     Gamergate
    -0.72
    ulner
    -0.71
    GBT
    -0.71
    ITNESS
    -0.70
    ļé
    -0.69
     Grayson
    -0.69
    POSITIVE LOGITS
     beans
    1.23
     berries
    1.21
     powder
    1.21
     syrup
    1.20
     mustard
    1.20
     sauce
    1.19
     seeds
    1.17
     noodles
    1.15
     flakes
    1.13
     soup
    1.13
    Activations Density 0.140%

    No Known Activations