© 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 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. 7474
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word "pants"

    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
    35
    +0.12
    0.6%
    415
    +0.10
    0.5%
    288
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    652
    +0.10
    0.02
    415
    +0.10
    0.01
    Negative Logits
     Scotia
    -0.81
     Flavoring
    -0.75
    KNOWN
    -0.75
     Galile
    -0.71
    inosaur
    -0.70
     Kern
    -0.67
    illery
    -0.67
    rian
    -0.65
    rious
    -0.63
     Democr
    -0.63
    POSITIVE LOGITS
     trousers
    1.10
     jeans
    1.07
    hirt
    1.06
     pants
    1.05
     sleeves
    1.01
     straps
    0.99
    uits
    0.97
     worn
    0.97
    pins
    0.97
    bag
    0.95
    Activations Density 0.028%

    No Known Activations