© 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. 4972
    Prev
    Next
    INDEX
    Explanations

    terms related to geography and geopolitics, particularly focusing on continental 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
    515
    +0.13
    0.6%
    429
    +0.09
    0.4%
    256
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    515
    +0.13
    0.03
    288
    +0.09
    0.03
    701
    +0.09
    0.02
    Negative Logits
    argon
    -0.84
    HOU
    -0.81
    emark
    -0.77
    oru
    -0.76
    olith
    -0.76
    nington
    -0.74
    uden
    -0.73
    fully
    -0.73
    ocracy
    -0.73
    udeb
    -0.73
    POSITIVE LOGITS
     travel
    1.03
     flights
    1.00
     travelers
    0.92
     commerce
    0.88
     journeys
    0.88
     communication
    0.86
     airliner
    0.86
     trips
    0.86
     transport
    0.85
     connections
    0.85
    Activations Density 0.088%

    No Known Activations