© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 19529
    Prev
    Next
    INDEX
    Explanations

    phrases related to birds, specifically auks and their characteristics

    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
    481
    +0.32
    1.5%
    447
    +0.22
    1.1%
    763
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.32
    0.05
    579
    +0.22
    0.04
    343
    +0.08
    0.04
    Negative Logits
    orders
    -0.60
     unse
    -0.56
     stalls
    -0.56
    achine
    -0.55
    actual
    -0.53
    sein
    -0.53
    ordering
    -0.52
     dogs
    -0.52
    boys
    -0.51
     kittens
    -0.51
    POSITIVE LOGITS
    vantage
    0.84
    Pacific
    0.79
    etus
    0.77
    vironment
    0.75
    ument
    0.73
    gypt
    0.72
    ÃĽ
    0.72
    oola
    0.71
    haar
    0.68
    Lago
    0.68
    Activations Density 0.401%

    No Known Activations