© 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 EvalsExportsinterp-engineNEWAPI 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. 22664
    Prev
    Next
    INDEX
    Explanations

    mentions of President Trump and related political figures or events

    oai_token-act-pair · gpt-4o-miniTriggered 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
    430
    +0.14
    0.6%
    447
    +0.13
    0.6%
    466
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    430
    +0.14
    0.04
    466
    +0.13
    0.04
    224
    +0.10
    0.04
    Negative Logits
    MJ
    -0.77
    PsyNetMessage
    -0.73
    MpServer
    -0.72
     Sleeping
    -0.68
    driving
    -0.68
    ãĥ¼ãĥĨ
    -0.68
    ãĥ¼ãĥĨãĤ£
    -0.67
    NP
    -0.66
    ãĤ¯
    -0.64
     Schl
    -0.64
    POSITIVE LOGITS
     vetoed
    0.94
     appoint
    0.88
     congratulated
    0.85
    ÃŃs
    0.85
     appointed
    0.83
     announced
    0.82
     Jinping
    0.82
     toured
    0.81
     dispatched
    0.81
     pard
    0.80
    Activations Density 0.070%

    No Known Activations