© 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. 12126
    Prev
    Next
    INDEX
    Explanations

    mentions of specific names or titles

    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
    350
    +0.11
    0.5%
    556
    +0.10
    0.4%
    668
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    224
    +0.11
    0.04
    556
    +0.10
    0.03
    466
    +0.10
    0.03
    Negative Logits
     Jonah
    -0.71
    ype
    -0.64
     cock
    -0.63
    raltar
    -0.63
     Goat
    -0.63
     Plains
    -0.63
     dick
    -0.62
     Jericho
    -0.62
    ESE
    -0.62
     Canaan
    -0.62
    POSITIVE LOGITS
     herself
    1.32
    pher
    0.84
    athed
    0.83
    Anne
    0.77
    lled
    0.77
     lashes
    0.76
    athing
    0.75
     vagina
    0.75
     husband
    0.75
    Marie
    0.75
    Activations Density 0.068%

    No Known Activations