© 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. 5749
    Prev
    Next
    INDEX
    Explanations

    mentions of the video game series "Metal Gear Solid" 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
    385
    +0.12
    0.6%
    288
    +0.12
    0.6%
    649
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    289
    +0.12
    0.01
    67
    +0.12
    0.01
    288
    +0.10
    0.01
    Negative Logits
    zee
    -0.75
    ========
    -0.69
    lyn
    -0.67
     Nurs
    -0.64
     Meadows
    -0.63
     Rowling
    -0.63
    HCR
    -0.63
     Suc
    -0.62
    ctors
    -0.61
     Dhabi
    -0.61
    POSITIVE LOGITS
    anguage
    1.61
     detectors
    1.25
     oxide
    1.20
     detector
    1.08
    works
    1.07
    working
    0.98
    heads
    0.96
    bending
    0.95
    ica
    0.95
    urgical
    0.92
    Activations Density 0.015%

    No Known Activations