© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    phrases related to critique or assessment

    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
    629
    +0.11
    0.5%
    253
    +0.10
    0.4%
    397
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    397
    +0.11
    0.03
    41
    +0.10
    0.02
    259
    +0.10
    0.02
    Negative Logits
    FTWARE
    -0.70
    iller
    -0.68
    EStream
    -0.65
    VIDEO
    -0.62
    arthy
    -0.59
    ilet
    -0.59
    ilaterally
    -0.57
    planes
    -0.57
    gio
    -0.57
     cryst
    -0.57
    POSITIVE LOGITS
    athe
    0.74
    hi
    0.69
    inventoryQuantity
    0.68
    lihood
    0.66
     Yor
    0.56
    ©¶æ
    0.54
    ados
    0.54
    ãĤ¦
    0.53
     Beaver
    0.52
    ovie
    0.52
    Activations Density 0.088%

    No Known Activations