© 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. 13675
    Prev
    Next
    INDEX
    Explanations

    phrases related to royalty or organizations with the word "Royal" in them

    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
    472
    +0.14
    0.6%
    464
    +0.12
    0.5%
    290
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    472
    +0.14
    0.02
    464
    +0.12
    0.02
    290
    +0.10
    0.02
    Negative Logits
    orer
    -0.81
    alach
    -0.77
    ombies
    -0.72
    oldemort
    -0.70
    omsky
    -0.70
     Gutenberg
    -0.69
    arers
    -0.69
    printf
    -0.68
    icago
    -0.67
    arella
    -0.67
    POSITIVE LOGITS
    ty
    1.00
     Palace
    0.84
     Caribbean
    0.79
     Arabia
    0.76
     Warrant
    0.75
    ton
    0.72
     Royal
    0.72
     Navy
    0.72
     Chall
    0.71
     Oak
    0.70
    Activations Density 0.021%

    No Known Activations