© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 14298
    Prev
    Next
    INDEX
    Explanations

    phrases indicating admiration or praise

    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
    447
    +0.13
    0.6%
    723
    +0.12
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    723
    +0.13
    0.04
    170
    +0.12
    0.04
    512
    +0.10
    0.04
    Negative Logits
    hung
    -0.66
    agues
    -0.62
    ievers
    -0.61
    perate
    -0.61
    ansen
    -0.61
    eor
    -0.61
    wrote
    -0.61
    iti
    -0.61
    urch
    -0.59
    en
    -0.59
    POSITIVE LOGITS
     undoubtedly
    0.91
     sheer
    0.84
     longevity
    0.81
     namely
    0.78
     evidenced
    0.78
     indeed
    0.77
     how
    0.76
     simplicity
    0.74
     doubtless
    0.73
     borne
    0.72
    Activations Density 0.110%

    No Known Activations