© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 7946
    Prev
    Next
    INDEX
    Explanations

    information related to historical events and conflicts

    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
    91
    +0.11
    0.5%
    686
    +0.10
    0.5%
    637
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.11
    0.09
    608
    +0.10
    0.08
    686
    +0.10
    0.04
    Negative Logits
    quickShipAvailable
    -0.76
    FIG
    -0.76
    iple
    -0.75
     ðŁij
    -0.74
    FIN
    -0.72
    VPN
    -0.72
    itialized
    -0.71
     FANTASY
    -0.71
     partName
    -0.70
    epad
    -0.70
    POSITIVE LOGITS
     wartime
    1.02
     postwar
    0.97
     impoverished
    0.95
     colonial
    0.94
     apartheid
    0.92
     Soviet
    0.90
     famine
    0.89
     villages
    0.88
     colony
    0.86
     communism
    0.86
    Activations Density 0.705%

    No Known Activations