© 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. 11027
    Prev
    Next
    INDEX
    Explanations

    phrases related to political issues or investigations

    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
    +0.48
    2.7%
    64
    +0.11
    0.6%
    694
    +0.09
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.48
    -0.02
    711
    +0.11
    0.04
    575
    +0.09
    0.09
    Negative Logits
     partName
    -0.56
    quickShipAvailable
    -0.52
    epad
    -0.52
    >(
    -0.51
    assetsadobe
    -0.50
    bnb
    -0.50
    */(
    -0.49
     aback
    -0.48
    iple
    -0.48
     denotes
    -0.47
    POSITIVE LOGITS
    Ħ¢
    0.55
    thood
    0.53
    .''.
    0.51
    assault
    0.51
     ObamaCare
    0.50
    amphetamine
    0.49
     blight
    0.49
     doping
    0.49
     insurrection
    0.47
     unfairly
    0.47
    Activations Density 2.030%

    No Known Activations