© 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. 2616
    Prev
    Next
    INDEX
    Explanations

    phrases related to locations, particularly hospitals, cities, and specific places

    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
    87
    +0.42
    2.5%
    620
    +0.10
    0.6%
    393
    +0.10
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.42
    0.12
    608
    +0.10
    0.13
    87
    +0.10
    -0.02
    Negative Logits
    ickr
    -0.60
     Cosponsors
    -0.57
    inventoryQuantity
    -0.55
     partName
    -0.55
     PLEASE
    -0.50
     Originally
    -0.50
    NN
    -0.50
    resy
    -0.49
    MpServer
    -0.48
    BILL
    -0.48
    POSITIVE LOGITS
     their
    0.63
     theirs
    0.60
     respective
    0.57
     respectively
    0.56
     those
    0.55
     nearby
    0.54
     humankind
    0.53
     them
    0.53
     domestic
    0.52
     eventual
    0.52
    Activations Density 1.229%

    No Known Activations