© 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. 10387
    Prev
    Next
    INDEX
    Explanations

    mentions of chemical reactions and processes

    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
    649
    +0.10
    0.5%
    526
    +0.09
    0.4%
    484
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    659
    +0.09
    0.03
    343
    +0.09
    0.02
    Negative Logits
     Shades
    -0.72
     permission
    -0.70
     Lauder
    -0.69
     Apprentice
    -0.67
    ATURES
    -0.67
     quarters
    -0.66
     fries
    -0.66
    ++++++++++++++++
    -0.64
     disemb
    -0.62
     rece
    -0.61
    POSITIVE LOGITS
    nard
    1.13
    fam
    1.10
    idation
    1.08
    imity
    1.04
    eus
    1.00
    ilon
    0.94
    eda
    0.91
    ipedia
    0.89
    es
    0.89
    edo
    0.88
    Activations Density 0.130%

    No Known Activations