© 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. 11056
    Prev
    Next
    INDEX
    Explanations

    phrases related to physical appearance and characteristics, particularly focusing on references to blonde hair

    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
    144
    +0.11
    0.5%
    343
    +0.11
    0.5%
    212
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.11
    0.01
    326
    +0.11
    0.01
    212
    +0.10
    0.01
    Negative Logits
    llah
    -0.84
     Flavoring
    -0.82
    afort
    -0.82
    inventoryQuantity
    -0.81
    apego
    -0.79
    ablishment
    -0.77
    arium
    -0.76
    EMS
    -0.73
    GAN
    -0.73
    iazep
    -0.72
    POSITIVE LOGITS
     wig
    1.34
     blond
    1.16
     blonde
    1.06
    haired
    1.05
     hair
    1.01
     bombshell
    1.00
     girl
    0.93
    beard
    0.93
     babe
    0.91
     bob
    0.91
    Activations Density 0.030%

    No Known Activations