© 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 49152
    9. 8-RES_FS49152-JB
    11. 41569
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals, particularly names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    87
    +0.35
    1.9%
    481
    +0.14
    0.8%
    659
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.35
    0.08
    700
    +0.14
    0.07
    502
    +0.14
    0.06
    Negative Logits
    izoph
    -0.55
     polar
    -0.54
    Xi
    -0.54
     unsustainable
    -0.54
     apex
    -0.53
    Scotland
    -0.53
    Temperature
    -0.53
     entail
    -0.52
     unfavorable
    -0.51
     ultras
    -0.51
    POSITIVE LOGITS
     Jr
    1.14
    baum
    1.00
    witz
    0.96
    owski
    0.94
    meyer
    0.93
    berger
    0.92
    lein
    0.91
    baugh
    0.91
    owicz
    0.90
    bach
    0.89
    Activations Density 0.170%

    No Known Activations