© 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 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. 12320
    Prev
    Next
    INDEX
    Explanations

    mentions of universities, political positions, and political affiliations

    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
    616
    +0.12
    0.5%
    325
    +0.09
    0.4%
    392
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.12
    0.07
    99
    +0.09
    0.04
    325
    +0.09
    0.05
    Negative Logits
     DOJ
    -0.91
     unfavorable
    -0.85
     Navajo
    -0.85
    LOS
    -0.82
     maneuver
    -0.82
     FDA
    -0.79
     favorable
    -0.78
     favored
    -0.78
    FBI
    -0.77
    izations
    -0.77
    POSITIVE LOGITS
    shire
    1.37
     Edinburgh
    1.26
     centre
    1.24
    inburgh
    1.23
     £
    1.21
    emouth
    1.19
     Albion
    1.17
     Yorkshire
    1.15
     Centre
    1.15
     harbour
    1.14
    Activations Density 0.300%

    No Known Activations