© 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. 22949
    Prev
    Next
    INDEX
    Explanations

    references to coastal regions and guards

    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
    526
    +0.12
    0.6%
    288
    +0.10
    0.5%
    659
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    693
    +0.12
    0.02
    104
    +0.10
    0.02
    701
    +0.10
    0.02
    Negative Logits
    chel
    -0.74
    DonaldTrump
    -0.74
    thood
    -0.73
     Parenthood
    -0.70
    akia
    -0.68
    Lens
    -0.65
    VK
    -0.64
    tered
    -0.64
    cca
    -0.63
    VL
    -0.63
    POSITIVE LOGITS
    lines
    1.13
     coast
    0.94
    line
    0.90
    guard
    0.85
     Coast
    0.85
    side
    0.84
    ographically
    0.82
     Mariners
    0.82
    guards
    0.81
    west
    0.80
    Activations Density 0.027%

    No Known Activations