© 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. 8209
    Prev
    Next
    INDEX
    Explanations

    phone numbers in the format of area code and phone numbers with certain digits

    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
    7
    +0.12
    0.5%
    562
    +0.09
    0.4%
    709
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    310
    +0.09
    0.03
    230
    +0.09
    0.02
    Negative Logits
    istically
    -0.80
    estine
    -0.74
    think
    -0.68
     Sands
    -0.67
     Proposition
    -0.64
    owicz
    -0.62
    deen
    -0.61
    uyomi
    -0.61
    wing
    -0.60
    holder
    -0.59
    POSITIVE LOGITS
     ILCS
    1.05
    mph
    0.92
     dB
    0.82
    20439
    0.80
    rup
    0.79
    00000
    0.78
    é¾
    0.73
    70
    0.71
    503
    0.71
    00
    0.71
    Activations Density 0.043%

    No Known Activations