© 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. 8947
    Prev
    Next
    INDEX
    Explanations

    words related to unintended or unwanted consequences/results

    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
    655
    +0.10
    0.5%
    763
    +0.10
    0.5%
    151
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.10
    0.04
    763
    +0.10
    0.03
    408
    +0.10
    0.03
    Negative Logits
    ardless
    -0.88
    emark
    -0.88
    eworks
    -0.87
    cius
    -0.82
    uits
    -0.81
    imore
    -0.80
    sheet
    -0.79
    lass
    -0.79
    anguage
    -0.77
    ickr
    -0.76
    POSITIVE LOGITS
     pregnancies
    1.15
     consequence
    1.09
     consequences
    1.00
     complication
    0.98
     pregnancy
    0.97
     Parenthood
    0.90
     unintended
    0.84
     collateral
    0.81
     burden
    0.81
     surprises
    0.81
    Activations Density 0.076%

    No Known Activations