© 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. 12391
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations or cities, especially Los Angeles

    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
    649
    +0.09
    0.4%
    152
    +0.09
    0.4%
    12
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.09
    0.03
    306
    +0.09
    0.03
    152
    +0.09
    0.03
    Negative Logits
    ebook
    -0.77
    BOOK
    -0.69
    oulos
    -0.67
     miscarriage
    -0.67
    ICLE
    -0.66
     tremend
    -0.64
    stroke
    -0.63
     variance
    -0.63
     recognition
    -0.63
     calculus
    -0.61
    POSITIVE LOGITS
     Angeles
    1.67
     Alam
    1.04
     Santos
    0.98
    ction
    0.91
     Aires
    0.90
     Padres
    0.90
    ites
    0.88
     ANGEL
    0.88
    ctions
    0.85
    Angel
    0.84
    Activations Density 0.017%

    No Known Activations