© 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. 19623
    Prev
    Next
    INDEX
    Explanations

    connections or links between concepts or entities

    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
    549
    +0.15
    0.7%
    608
    +0.14
    0.6%
    346
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    549
    +0.15
    0.03
    608
    +0.14
    0.03
    616
    +0.10
    0.02
    Negative Logits
    quished
    -0.94
    \\\\\\\\
    -0.88
    OGR
    -0.83
    TPPStreamerBot
    -0.79
    ////////////////
    -0.78
    stal
    -0.76
    nell
    -0.75
    abases
    -0.74
    dp
    -0.73
    entimes
    -0.73
    POSITIVE LOGITS
     sexes
    0.81
     criminality
    0.75
     genders
    0.75
     these
    0.75
     ethnicity
    0.74
     disparate
    0.70
     academics
    0.67
     humans
    0.67
     counties
    0.67
     geography
    0.66
    Activations Density 0.029%

    No Known Activations