© 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. 6106
    Prev
    Next
    INDEX
    Explanations

    scientific and medical terms related to inflammation, health, and experimental procedures

    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
    516
    +0.12
    0.5%
    255
    +0.11
    0.5%
    182
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    516
    +0.12
    0.04
    255
    +0.11
    0.04
    724
    +0.11
    0.04
    Negative Logits
     Manor
    -0.89
    fell
    -0.79
    soDeliveryDate
    -0.77
    EVA
    -0.75
    ãĥĩãĤ£
    -0.73
    ounge
    -0.71
    pants
    -0.71
    Weather
    -0.71
    pees
    -0.70
    iquette
    -0.70
    POSITIVE LOGITS
     inhibition
    1.41
     inhibitor
    1.38
     inhibitors
    1.35
     enzymes
    1.33
     enzyme
    1.33
     mRNA
    1.27
     mediated
    1.26
     proteins
    1.25
     inhibit
    1.23
     pept
    1.19
    Activations Density 0.209%

    No Known Activations