© 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. 21288
    Prev
    Next
    INDEX
    Explanations

    words related to a specific event or incident involving Malaysian Airlines and related nations

    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
    288
    +0.15
    0.7%
    481
    +0.13
    0.6%
    643
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.15
    0.02
    643
    +0.13
    0.01
    757
    +0.10
    0.01
    Negative Logits
    á½
    -0.72
    bern
    -0.70
    ptions
    -0.66
    velt
    -0.64
    coat
    -0.63
    BAT
    -0.63
    ents
    -0.62
    enegger
    -0.61
    tops
    -0.60
     brut
    -0.59
    POSITIVE LOGITS
     Lumpur
    1.69
     Airlines
    1.30
    colm
    0.89
     airliner
    0.87
     airlines
    0.81
    awi
    0.81
    daq
    0.80
    aimon
    0.79
    ovic
    0.79
    vati
    0.77
    Activations Density 0.028%

    No Known Activations