© 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. 16725
    Prev
    Next
    INDEX
    Explanations

    information related to potential health threats and epidemics, as well as military and security topics with a focus on specific countries and regions

    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
    218
    +0.14
    0.6%
    265
    +0.11
    0.5%
    481
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.14
    0.06
    298
    +0.11
    0.05
    265
    +0.11
    0.05
    Negative Logits
    ĸļ
    -0.99
    iture
    -0.88
    endars
    -0.82
    cknow
    -0.81
    ruary
    -0.79
    issance
    -0.78
    appointed
    -0.76
    itures
    -0.75
    cean
    -0.74
    Finish
    -0.73
    POSITIVE LOGITS
     pathogens
    1.43
     toxins
    1.35
     malware
    1.34
     terrorists
    1.33
     viruses
    1.31
     virus
    1.29
     infection
    1.27
     terrorist
    1.27
     disease
    1.26
     infectious
    1.23
    Activations Density 0.742%

    No Known Activations