© 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 EvalsExportsinterp-engineNEWAPI 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. 22942
    Prev
    Next
    INDEX
    Explanations

    references to specific ethnic or religious identities in the context of systemic issues or conflicts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.11
    0.5%
    590
    +0.08
    0.4%
    124
    +0.08
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.11
    0.03
    401
    +0.08
    0.04
    288
    +0.08
    0.04
    Negative Logits
    inventoryQuantity
    -0.83
    ascript
    -0.80
    quickShipAvailable
    -0.80
    eus
    -0.71
    cially
    -0.71
    pter
    -0.68
     Turing
    -0.68
    etting
    -0.67
    ccoli
    -0.67
    efully
    -0.67
    POSITIVE LOGITS
     tribe
    0.95
     tribes
    0.94
     nationalists
    0.93
     separatists
    0.92
     villagers
    0.92
     Tribe
    0.91
     tribal
    0.89
    istani
    0.89
     ancestry
    0.89
     warrior
    0.89
    Activations Density 0.200%

    No Known Activations