© 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. 14641
    Prev
    Next
    INDEX
    Explanations

    references to mental health and regulations related to mental health

    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
    575
    +0.12
    0.6%
    288
    +0.12
    0.5%
    755
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    755
    +0.12
    0.02
    578
    +0.12
    0.02
    575
    +0.12
    0.02
    Negative Logits
    advertisement
    -0.78
    ICA
    -0.75
    ded
    -0.69
    gger
    -0.68
    mint
    -0.65
    Buy
    -0.65
    eled
    -0.65
    ELS
    -0.65
    Shop
    -0.65
    hire
    -0.64
    POSITIVE LOGITS
     illness
    1.05
     faculties
    0.97
     disorders
    0.94
     anguish
    0.94
     defic
    0.91
     disorder
    0.89
    izing
    0.89
     wellbeing
    0.87
    ities
    0.85
     illnesses
    0.85
    Activations Density 0.015%

    No Known Activations