© 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. 10240
    Prev
    Next
    INDEX
    Explanations

    words related to political conflicts and disputes

    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
    447
    +0.17
    0.8%
    658
    +0.12
    0.5%
    546
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    658
    +0.17
    0.03
    288
    +0.12
    0.04
    243
    +0.11
    0.03
    Negative Logits
    ITNESS
    -0.83
    iaries
    -0.70
    lein
    -0.70
    200000
    -0.69
    elta
    -0.69
    oken
    -0.67
    Delivery
    -0.67
    hetically
    -0.67
    leeve
    -0.66
    itely
    -0.66
    POSITIVE LOGITS
     factions
    1.04
     between
    0.99
     rift
    0.94
     partisans
    0.94
     politics
    0.92
     alliances
    0.91
     ideologies
    0.85
     divides
    0.83
     animosity
    0.82
    isans
    0.81
    Activations Density 0.107%

    No Known Activations