© 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. 18196
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences beginning with the word "whose."

    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
    0.6%
    493
    +0.11
    0.5%
    453
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    493
    +0.12
    0.02
    453
    +0.11
    0.02
    543
    +0.11
    0.02
    Negative Logits
    wei
    -0.77
    yi
    -0.76
    DT
    -0.73
    edd
    -0.73
    Alert
    -0.72
    brush
    -0.71
    CLASS
    -0.70
    ets
    -0.69
    eat
    -0.69
     Related
    -0.68
    POSITIVE LOGITS
     sole
    1.17
     ancestors
    1.15
     own
    1.05
     whereabouts
    1.00
     parents
    0.94
     opinions
    0.92
     grandparents
    0.91
     name
    0.91
     penchant
    0.91
     aim
    0.90
    Activations Density 0.040%

    No Known Activations