© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 8984
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial topics or actions

    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
    570
    +0.12
    0.5%
    481
    +0.10
    0.5%
    366
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    366
    +0.12
    0.03
    288
    +0.10
    0.04
    485
    +0.10
    0.03
    Negative Logits
    idth
    -0.68
    Shares
    -0.68
     Niet
    -0.60
     [+]
    -0.59
    assetsadobe
    -0.57
    cheon
    -0.57
    76561
    -0.57
     hrs
    -0.56
    illard
    -0.56
    saw
    -0.56
    POSITIVE LOGITS
     disappear
    0.95
     obsolete
    0.94
     happen
    0.93
     accessible
    0.93
     unavailable
    0.89
     inaccessible
    0.85
     easier
    0.83
     redundant
    0.83
     safer
    0.82
    solete
    0.79
    Activations Density 0.202%

    No Known Activations