© 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. 14261
    Prev
    Next
    INDEX
    Explanations

    addresses with specifiers like 'Ave', 'Avenue', and 'Way'

    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
    +0.30
    1.5%
    464
    +0.12
    0.6%
    519
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    316
    +0.30
    0.04
    464
    +0.12
    0.04
    87
    +0.10
    -0.01
    Negative Logits
    Reviewer
    -0.66
    ".[
    -0.61
     Flavoring
    -0.59
    DragonMagazine
    -0.59
     weld
    -0.57
     Logged
    -0.57
    actionDate
    -0.56
     reconc
    -0.55
    duino
    -0.54
    STDOUT
    -0.54
    POSITIVE LOGITS
    ensis
    0.66
     Jr
    0.66
    Jr
    0.65
    imus
    0.61
    /?
    0.60
     Featuring
    0.59
    ogie
    0.58
     fame
    0.58
    ;
    0.57
     &&
    0.56
    Activations Density 0.346%

    No Known Activations