© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 18588
    Prev
    Next
    INDEX
    Explanations

    phrases expressing pride or boasting about something

    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
    669
    +0.14
    0.6%
    723
    +0.10
    0.4%
    280
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.14
    0.03
    608
    +0.10
    0.03
    723
    +0.09
    0.02
    Negative Logits
    soDeliveryDate
    -1.02
    MRI
    -0.84
     guiActiveUn
    -0.74
    scan
    -0.68
    uto
    -0.68
     downward
    -0.65
    interrupted
    -0.63
    iaz
    -0.63
    wang
    -0.62
    esthetic
    -0.61
    POSITIVE LOGITS
     accomplishments
    1.10
     accomplishment
    0.93
     achievements
    0.91
     bravery
    0.86
     individuality
    0.78
     superiority
    0.77
     Achievement
    0.74
     feat
    0.73
     proudly
    0.73
     heroism
    0.73
    Activations Density 0.095%

    No Known Activations