© 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. 17468
    Prev
    Next
    INDEX
    Explanations

    references to the Guantanamo Bay detention camp and related terms

    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
    +0.11
    0.5%
    447
    +0.10
    0.5%
    420
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    633
    +0.11
    0.03
    584
    +0.10
    0.03
    125
    +0.10
    0.03
    Negative Logits
     toast
    -0.92
     Toast
    -0.89
     Motorsport
    -0.82
    natureconservancy
    -0.79
    wcsstore
    -0.75
    soType
    -0.74
    Shares
    -0.73
     eclipse
    -0.73
     gol
    -0.72
     sunscreen
    -0.70
    POSITIVE LOGITS
     detainees
    1.44
     prisons
    1.42
     detention
    1.41
     confinement
    1.40
     inmates
    1.36
     jails
    1.34
     Guantanamo
    1.31
     prisoners
    1.30
     interrogation
    1.30
     detainee
    1.29
    Activations Density 0.277%

    No Known Activations