© 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. 5133
    Prev
    Next
    INDEX
    Explanations

    locations or entities related to geopolitical events

    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
    127
    +0.12
    0.5%
    605
    +0.11
    0.5%
    353
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    605
    +0.12
    0.03
    401
    +0.11
    0.04
    353
    +0.09
    0.03
    Negative Logits
    cause
    -0.82
    ITCH
    -0.78
     Patreon
    -0.74
    etheless
    -0.70
    oday
    -0.66
    soType
    -0.65
    !:
    -0.64
    ¶ħ
    -0.63
    >:
    -0.61
    acea
    -0.61
    POSITIVE LOGITS
     resides
    1.19
     resided
    1.04
     shines
    0.97
     reside
    0.97
     intersect
    0.93
     meets
    0.91
     excel
    0.89
     enters
    0.86
     awaited
    0.86
     originated
    0.86
    Activations Density 0.272%

    No Known Activations