© 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. 7799
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to companies or people

    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
    207
    +0.13
    0.6%
    50
    +0.10
    0.5%
    265
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.13
    0.03
    659
    +0.10
    0.03
    667
    +0.10
    0.02
    Negative Logits
     awa
    -0.76
     Independence
    -0.74
     indist
    -0.72
     FORM
    -0.72
     Connie
    -0.71
     recre
    -0.70
     Edmund
    -0.69
    accompan
    -0.69
     Mystic
    -0.68
     CON
    -0.68
    POSITIVE LOGITS
    z
    1.72
    zos
    1.43
    zan
    1.42
    zon
    1.40
    Z
    1.38
    zes
    1.37
    zie
    1.35
    zu
    1.34
    zo
    1.33
    zing
    1.32
    Activations Density 0.070%

    No Known Activations