© 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. 20583
    Prev
    Next
    INDEX
    Explanations

    email subjects

    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
    97
    +0.10
    0.5%
    641
    +0.09
    0.4%
    640
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.10
    0.03
    23
    +0.09
    0.02
    411
    +0.09
    0.02
    Negative Logits
    oval
    -0.87
    ula
    -0.79
    ozo
    -0.78
    formation
    -0.77
    ult
    -0.69
    oust
    -0.65
    alde
    -0.65
    ared
    -0.65
    uve
    -0.64
    harm
    -0.64
    POSITIVE LOGITS
     CTR
    0.81
     Unknown
    0.72
     ç¥ŀ
    0.71
     CONTROL
    0.69
     SCP
    0.68
     [*]
    0.67
     Previous
    0.66
     Detected
    0.66
     Potato
    0.66
     guiName
    0.66
    Activations Density 0.053%

    No Known Activations