© 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. 8892
    Prev
    Next
    INDEX
    Explanations

    the word "this" in various contexts

    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
    393
    +0.11
    0.5%
    159
    +0.11
    0.5%
    589
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    159
    +0.11
    0.04
    767
    +0.11
    0.04
    521
    +0.10
    0.03
    Negative Logits
    bats
    -0.79
    Ĭ±
    -0.79
    Īè
    -0.72
    ãĥīãĥ©
    -0.71
    ©¶æ¥µ
    -0.70
    aus
    -0.70
    resp
    -0.67
     Izan
    -0.67
    Band
    -0.67
     Towers
    -0.66
    POSITIVE LOGITS
     article
    1.05
     ARTICLE
    1.03
     week
    0.87
     month
    0.85
     slideshow
    0.80
     blog
    0.80
     topic
    0.77
     particular
    0.77
     page
    0.77
     year
    0.75
    Activations Density 0.075%

    No Known Activations