© 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. 13205
    Prev
    Next
    INDEX
    Explanations

    mental health disorders and related terms

    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
    481
    +0.14
    0.7%
    288
    +0.10
    0.5%
    163
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    762
    +0.14
    0.02
    288
    +0.10
    0.02
    235
    +0.10
    0.02
    Negative Logits
    stanbul
    -0.75
     snipp
    -0.71
    baugh
    -0.68
    riel
    -0.68
    raltar
    -0.67
     Hilton
    -0.67
    Sources
    -0.66
    mination
    -0.66
    endars
    -0.63
    gall
    -0.63
    POSITIVE LOGITS
     diagnoses
    1.06
     diagnosis
    0.99
     symptoms
    0.96
     Symptoms
    0.93
     worsen
    0.93
     disorders
    0.91
     spectrum
    0.89
     predis
    0.87
     suff
    0.85
     Spectrum
    0.85
    Activations Density 0.034%

    No Known Activations