© 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. 13923
    Prev
    Next
    INDEX
    Explanations

    dates in dd/mm format

    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
    481
    +0.26
    1.2%
    193
    +0.10
    0.5%
    178
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    380
    +0.26
    0.04
    43
    +0.10
    0.04
    561
    +0.09
    0.05
    Negative Logits
    ãĤ´ãĥ³
    -0.81
    inventoryQuantity
    -0.78
     redes
    -0.73
    itto
    -0.65
    arah
    -0.63
    qus
    -0.62
    ãĥ¥
    -0.62
     included
    -0.60
    catentry
    -0.59
    EStream
    -0.58
    POSITIVE LOGITS
     Plaintiff
    0.80
     VICE
    0.68
     Samantha
    0.67
     Dominic
    0.65
     Stephanie
    0.64
     Veronica
    0.63
    when
    0.63
     Nathaniel
    0.62
     demonstrators
    0.62
     organizers
    0.61
    Activations Density 0.191%

    No Known Activations