© 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. 5098
    Prev
    Next
    INDEX
    Explanations

    words related to viruses and medical research

    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
    +0.12
    0.6%
    537
    +0.10
    0.5%
    288
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    346
    +0.12
    0.01
    473
    +0.10
    0.01
    537
    +0.10
    0.01
    Negative Logits
    fman
    -0.97
    notations
    -0.77
    anooga
    -0.77
    secut
    -0.77
    ilts
    -0.75
    alty
    -0.74
    eatures
    -0.71
    baugh
    -0.67
    ancies
    -0.66
    ixel
    -0.66
    POSITIVE LOGITS
     infection
    1.10
     infections
    1.07
    irus
    1.06
     outbreak
    1.00
     outbreaks
    0.93
     viruses
    0.93
     virus
    0.93
    infect
    0.92
     infect
    0.91
     disease
    0.88
    Activations Density 0.019%

    No Known Activations