© 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. 16317
    Prev
    Next
    INDEX
    Explanations

    references to historical figures, events, and locations, particularly in the context of political 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
    703
    +0.12
    0.5%
    475
    +0.10
    0.5%
    77
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.04
    659
    +0.10
    0.03
    232
    +0.09
    0.03
    Negative Logits
    advertising
    -1.16
    Topics
    -1.15
    development
    -1.01
    competitive
    -0.99
    follow
    -0.97
    beat
    -0.96
    podcast
    -0.96
    developed
    -0.96
    Issue
    -0.96
    omnia
    -0.95
    POSITIVE LOGITS
     Hu
    0.91
     li
    0.88
     il
    0.85
     N
    0.84
     ll
    0.83
     IL
    0.83
     ful
    0.82
     ther
    0.82
     Ur
    0.82
     Ara
    0.82
    Activations Density 0.188%

    No Known Activations