© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7260
    Prev
    Next
    INDEX
    Explanations

    words related to men's fashion

    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
    +0.15
    0.7%
    11
    +0.09
    0.4%
    581
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    7
    +0.15
    0.02
    581
    +0.09
    0.01
    11
    +0.09
    0.01
    Negative Logits
     Scotia
    -0.65
     Tinker
    -0.64
     Doodle
    -0.63
    ts
    -0.62
    bral
    -0.61
    amaz
    -0.60
    llan
    -0.60
     Able
    -0.60
     McAuliffe
    -0.60
    zzi
    -0.60
    POSITIVE LOGITS
    manship
    0.93
    umer
    0.92
    chen
    0.90
    orship
    0.90
    urable
    0.89
    burgh
    0.87
    ource
    0.86
    hift
    0.85
    haw
    0.84
    terday
    0.84
    Activations Density 0.024%

    No Known Activations