© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 9397
    Prev
    Next
    INDEX
    Explanations

    references to airport security and incidents related to airport locations, specifically Heathrow

    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
    420
    +0.13
    0.6%
    288
    +0.13
    0.6%
    99
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.13
    0.01
    420
    +0.13
    0.01
    628
    +0.12
    0.01
    Negative Logits
    uyomi
    -0.96
    acters
    -0.93
    itive
    -0.77
    ãĥ£
    -0.75
    pmwiki
    -0.71
    izable
    -0.71
    ctory
    -0.66
    ensional
    -0.65
    ifier
    -0.64
    imester
    -0.64
    POSITIVE LOGITS
    row
    0.89
    gow
    0.87
    stones
    0.84
    ocratic
    0.84
    brook
    0.83
    combe
    0.81
     Slater
    0.81
     Heath
    0.81
    rower
    0.80
    mare
    0.79
    Activations Density 0.025%

    No Known Activations