© 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. 22300
    Prev
    Next
    INDEX
    Explanations

    medical terms related to health conditions and their effects on the body

    oai_token-act-pair · gpt-4o-miniTriggered 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
    447
    +0.12
    0.5%
    452
    +0.11
    0.5%
    548
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    166
    +0.12
    0.04
    288
    +0.11
    0.04
    516
    +0.10
    0.03
    Negative Logits
    ilitary
    -0.91
     Tradable
    -0.85
    ivals
    -0.75
    aturday
    -0.74
    enance
    -0.72
     Konami
    -0.72
    vich
    -0.72
    ongo
    -0.71
    ionage
    -0.71
     Vide
    -0.69
    POSITIVE LOGITS
     disorders
    1.15
     inflammation
    1.15
     tissue
    1.09
     pathology
    1.08
     dysfunction
    1.08
     muc
    1.07
     circumference
    1.04
     Disorders
    1.01
     tissues
    1.01
     diseases
    0.97
    Activations Density 0.095%

    No Known Activations