© 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 3072
    9. 8-RES_FS3072-JB
    11. 260
    Prev
    Next
    INDEX
    Explanations

    names of people, likely actors or characters in movies

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    41
    +0.11
    0.5%
    369
    +0.09
    0.4%
    467
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.11
    232
    +0.09
    0.10
    41
    +0.09
    0.08
    Negative Logits
    catentry
    -0.74
    ilial
    -0.72
    ascript
    -0.68
    nces
    -0.64
    Versions
    -0.63
    redients
    -0.61
    OURCE
    -0.60
    inarily
    -0.60
    theless
    -0.58
    irlf
    -0.58
    POSITIVE LOGITS
     Lumpur
    1.03
    ikuman
    1.03
    enei
    0.91
    EStream
    0.90
    EStreamFrame
    0.87
    zie
    0.86
    lyak
    0.85
    inski
    0.84
    chuk
    0.80
    istan
    0.75
    Activations Density 1.217%

    No Known Activations