© 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. 10961
    Prev
    Next
    INDEX
    Explanations

    mentions of specific geographic locations

    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
    288
    +0.12
    0.5%
    169
    +0.11
    0.5%
    421
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    169
    +0.12
    0.02
    534
    +0.11
    0.02
    57
    +0.10
    0.02
    Negative Logits
    inventoryQuantity
    -0.82
    inger
    -0.80
    awaru
    -0.79
    enger
    -0.76
    ulative
    -0.74
    verb
    -0.73
    earance
    -0.73
    utenberg
    -0.73
    uable
    -0.72
    atted
    -0.72
    POSITIVE LOGITS
     Hemisphere
    1.30
     hemisphere
    1.18
     Lights
    1.09
     Ireland
    1.02
     Liberties
    1.02
     Territory
    0.97
     Caucasus
    0.86
    most
    0.86
     Territories
    0.84
     Californ
    0.79
    Activations Density 0.019%

    No Known Activations