© 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. 4894
    Prev
    Next
    INDEX
    Explanations

    specific lyrics from certain songs

    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
    570
    +0.09
    0.4%
    474
    +0.09
    0.4%
    553
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.09
    0.04
    29
    +0.09
    0.03
    767
    +0.09
    0.02
    Negative Logits
     whis
    -0.77
    woods
    -0.77
    cies
    -0.74
    bro
    -0.73
    anger
    -0.72
    cube
    -0.71
    kids
    -0.71
    ijah
    -0.69
    iaries
    -0.67
    eb
    -0.67
    POSITIVE LOGITS
     âĢ
    1.82
     **
    1.26
     ¶
    1.24
     «
    1.22
     âĶ
    1.22
     *
    1.21
     ***
    1.20
     ãĢĮ
    1.16
     â
    1.13
     >>
    1.11
    Activations Density 0.160%

    No Known Activations