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

    Neuronpedia

    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. 8616
    Prev
    Next
    INDEX
    Explanations

    words related to espionage or spy activities

    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
    578
    +0.11
    0.5%
    58
    +0.10
    0.4%
    342
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    291
    +0.11
    0.01
    58
    +0.10
    0.01
    538
    +0.09
    0.01
    Negative Logits
    urses
    -0.79
    ickr
    -0.77
    ktop
    -0.76
    aii
    -0.72
    keye
    -0.71
    artney
    -0.69
    TAIN
    -0.69
    agne
    -0.68
    ourse
    -0.65
    tin
    -0.65
    POSITIVE LOGITS
    moon
    1.03
    loo
    0.95
    boxing
    0.94
    runners
    0.90
    fax
    0.83
    stats
    0.82
    flame
    0.81
    hun
    0.77
    shadow
    0.75
    runner
    0.74
    Activations Density 0.016%

    No Known Activations