© 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. 19584
    Prev
    Next
    INDEX
    Explanations

    words related to military operations and conflicts in the Middle East

    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
    481
    +0.17
    0.8%
    24
    +0.14
    0.6%
    288
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.17
    0.04
    659
    +0.14
    0.04
    682
    +0.10
    0.03
    Negative Logits
    erest
    -0.76
     Phillies
    -0.75
     Vaugh
    -0.71
     Pengu
    -0.70
    PDATE
    -0.68
     Rockies
    -0.68
     Wilde
    -0.67
     pitchers
    -0.66
     resil
    -0.66
     ster
    -0.65
    POSITIVE LOGITS
    ayn
    1.15
    uddin
    1.12
    iyah
    1.07
    awi
    1.02
     Khan
    1.00
    qa
    0.98
     ibn
    0.97
     mosque
    0.96
    abad
    0.96
     Mosque
    0.96
    Activations Density 0.120%

    No Known Activations