© 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. 18307
    Prev
    Next
    INDEX
    Explanations

    information related to sports jerseys

    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
    343
    +0.12
    0.5%
    59
    +0.12
    0.5%
    83
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    678
    +0.12
    0.04
    764
    +0.12
    0.04
    59
    +0.10
    0.04
    Negative Logits
    tests
    -0.91
    enough
    -0.88
    lease
    -0.79
    ewater
    -0.77
    anship
    -0.77
    ratom
    -0.76
    Testing
    -0.76
    íķ
    -0.76
    phrine
    -0.75
    inki
    -0.75
    POSITIVE LOGITS
     logo
    1.37
     silhouette
    1.29
     motif
    1.25
     swast
    1.24
     inscription
    1.16
     embro
    1.16
     caption
    1.16
     logos
    1.16
     adorned
    1.16
     inscribed
    1.14
    Activations Density 0.624%

    No Known Activations