© 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. 6230
    Prev
    Next
    INDEX
    Explanations

    words related to traps and trap-related actions

    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
    549
    +0.14
    0.7%
    326
    +0.14
    0.6%
    0
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.14
    0.01
    549
    +0.14
    0.01
    288
    +0.11
    0.01
    Negative Logits
    edly
    -0.87
    issance
    -0.82
    sis
    -0.81
    itsch
    -0.68
    eda
    -0.68
    Merit
    -0.67
    eds
    -0.66
    care
    -0.66
    sburg
    -0.66
    verty
    -0.63
    POSITIVE LOGITS
    door
    1.43
    doors
    1.31
    finding
    0.86
    trap
    0.80
     traps
    0.80
    ERY
    0.75
    idon
    0.74
     trap
    0.72
     Labyrinth
    0.72
     unsuspecting
    0.72
    Activations Density 0.030%

    No Known Activations