© 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. 20952
    Prev
    Next
    INDEX
    Explanations

    news articles related to political and legal issues

    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
    502
    +0.16
    0.7%
    547
    +0.11
    0.5%
    235
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.16
    0.05
    502
    +0.11
    0.05
    547
    +0.10
    0.04
    Negative Logits
     Presidents
    -0.65
     Fortress
    -0.64
    ERC
    -0.64
     Ideal
    -0.63
     Ministers
    -0.62
    Scotland
    -0.59
     occupants
    -0.59
    istors
    -0.58
    Sold
    -0.58
    Council
    -0.57
    POSITIVE LOGITS
     (@
    0.97
     tweeted
    0.91
    iott
    0.84
     alerted
    0.83
     wondered
    0.82
    witz
    0.82
     Jr
    0.81
    aminer
    0.80
     headlined
    0.78
     wrote
    0.78
    Activations Density 0.127%

    No Known Activations