© 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 12288
    5. 8-RES_FS12288-JB
    6. 10404
    Prev
    Next
    INDEX
    Explanations

    the term or phrase that appears frequently in the text

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    101
    +0.09
    0.4%
    461
    +0.09
    0.4%
    603
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.09
    0.03
    552
    +0.09
    0.03
    312
    +0.08
    0.02
    Negative Logits
    jri
    -0.80
    ierrez
    -0.74
    oÄŁ
    -0.73
    ockets
    -0.67
    aples
    -0.66
    llah
    -0.64
    âĹ¼
    -0.64
    vic
    -0.64
     millenn
    -0.63
    phis
    -0.60
    POSITIVE LOGITS
     coined
    0.93
    ultimate
    0.90
     synonymous
    0.85
    ology
    0.81
    usage
    0.81
     '
    0.80
    plate
    0.79
    icide
    0.77
     itself
    0.76
     "-
    0.76
    Activations Density 0.101%

    No Known Activations