© 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. 8027
    Prev
    Next
    INDEX
    Explanations

    mentions of political conflicts and international events related to war and refugee crises

    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
    87
    +0.40
    2.3%
    373
    +0.16
    1.0%
    407
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.40
    0.07
    87
    +0.16
    -0.02
    232
    +0.09
    0.07
    Negative Logits
    ''.
    -0.53
    ".
    -0.50
    thood
    -0.50
    $.
    -0.49
     ".
    -0.46
     boil
    -0.45
    EStreamFrame
    -0.45
    .''.
    -0.45
    '.
    -0.44
     bluff
    -0.44
    POSITIVE LOGITS
     meanwhile
    0.57
     countered
    0.56
     wrote
    0.54
     reacted
    0.53
     commented
    0.53
     Fr
    0.53
     echoed
    0.52
    WARN
    0.51
     Vital
    0.50
     Ori
    0.49
    Activations Density 0.733%

    No Known Activations