© 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. 18469
    Prev
    Next
    INDEX
    Explanations

    mentions of Lady Gaga

    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
    99
    +0.10
    0.4%
    526
    +0.10
    0.4%
    404
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    99
    +0.10
    0.01
    325
    +0.10
    0.01
    18
    +0.09
    0.01
    Negative Logits
    osta
    -0.78
    aeda
    -0.74
    venants
    -0.73
    eger
    -0.72
    CAST
    -0.71
    ETF
    -0.67
    ozy
    -0.66
    riks
    -0.66
    quished
    -0.65
    ologically
    -0.64
    POSITIVE LOGITS
     Gaga
    1.40
    bug
    1.27
    bird
    1.12
    bugs
    1.11
    maid
    0.95
    birds
    0.91
    woman
    0.85
    cup
    0.83
    fing
    0.82
    parts
    0.82
    Activations Density 0.026%

    No Known Activations