© 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. 19408
    Prev
    Next
    INDEX
    Explanations

    phrases related to patriotism and national pride

    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
    592
    +0.11
    0.5%
    640
    +0.10
    0.5%
    179
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.11
    0.04
    160
    +0.10
    0.04
    179
    +0.10
    0.02
    Negative Logits
    ÄŁ
    -0.68
    odcast
    -0.66
    ptions
    -0.66
     McMaster
    -0.64
     turnover
    -0.62
     pdf
    -0.62
     basic
    -0.62
     decentral
    -0.62
     CMS
    -0.60
     extr
    -0.60
    POSITIVE LOGITS
    And
    0.90
     Where
    0.88
    Unt
    0.86
     Shall
    0.82
    Which
    0.82
    Were
    0.81
    ORN
    0.81
    Cause
    0.81
     Who
    0.79
    cause
    0.78
    Activations Density 0.121%

    No Known Activations