© 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. 1428
    Prev
    Next
    INDEX
    Explanations

    economic terms and data-related phrases

    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
    362
    +0.12
    0.5%
    454
    +0.12
    0.5%
    67
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.12
    0.06
    616
    +0.12
    0.04
    382
    +0.09
    0.03
    Negative Logits
    obyl
    -0.82
    kos
    -0.77
    iverse
    -0.74
    UTH
    -0.69
    enough
    -0.69
    sv
    -0.68
    HCR
    -0.67
     contam
    -0.67
     fate
    -0.67
    ADRA
    -0.65
    POSITIVE LOGITS
     each
    0.92
     OECD
    0.82
     respective
    0.77
     comparison
    0.73
     various
    0.73
     sectors
    0.71
     Continental
    0.70
     different
    0.69
     successive
    0.68
     Selected
    0.68
    Activations Density 0.266%

    No Known Activations