© 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. 7032
    Prev
    Next
    INDEX
    Explanations

    words related to ocean and water movement

    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
    263
    +0.15
    0.7%
    420
    +0.14
    0.7%
    377
    +0.14
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.15
    0.02
    30
    +0.14
    0.02
    288
    +0.14
    0.03
    Negative Logits
    ifax
    -0.85
    ional
    -0.83
    ite
    -0.79
    ivas
    -0.79
    istry
    -0.78
    ifer
    -0.77
    sson
    -0.76
    encers
    -0.75
    itic
    -0.73
    itory
    -0.73
    POSITIVE LOGITS
    bie
    0.83
    gger
    0.82
    chy
    0.76
    enhagen
    0.73
    driver
    0.70
    deen
    0.69
    drivers
    0.67
     Isles
    0.67
    ãģĨ
    0.67
     Carly
    0.67
    Activations Density 0.066%

    No Known Activations