© 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. 19726
    Prev
    Next
    INDEX
    Explanations

    references to sports events and game summaries

    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
    519
    +0.09
    0.4%
    761
    +0.09
    0.4%
    43
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.03
    326
    +0.09
    0.04
    232
    +0.08
    0.03
    Negative Logits
     Conserv
    -0.67
    ORK
    -0.60
     Genie
    -0.59
    LIST
    -0.56
     Debor
    -0.56
    .*
    -0.55
     Antar
    -0.54
     Primordial
    -0.54
     bearer
    -0.53
     FSA
    -0.53
    POSITIVE LOGITS
    "]=>
    0.73
    estamp
    0.70
    ocre
    0.70
    isode
    0.69
    phies
    0.69
    ĻĤ
    0.68
    imore
    0.68
    omore
    0.68
    roc
    0.68
    Us
    0.68
    Activations Density 0.162%

    No Known Activations