© 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. 19367
    Prev
    Next
    INDEX
    Explanations

    statements related to political issues and international relations

    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
    640
    +0.28
    1.4%
    87
    +0.16
    0.8%
    160
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    640
    +0.28
    0.16
    442
    +0.16
    0.14
    107
    +0.12
    0.13
    Negative Logits
     lifes
    -0.84
     nightly
    -0.75
     hero
    -0.73
     sucker
    -0.71
     stray
    -0.70
     bear
    -0.69
     instinct
    -0.69
     crush
    -0.69
     dolphin
    -0.68
     nomine
    -0.67
    POSITIVE LOGITS
    Finally
    1.76
    Regarding
    1.72
    Lastly
    1.70
    Furthermore
    1.69
    Moreover
    1.69
    However
    1.68
    Ultimately
    1.66
    Additionally
    1.63
    Nevertheless
    1.61
    Similarly
    1.59
    Activations Density 0.476%

    No Known Activations