© 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 12288
    9. 8-RES_FS12288-JB
    11. 1500
    Prev
    Next
    INDEX
    Explanations

    mentions of people's names and references to specific products or popular culture

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    393
    +0.12
    0.6%
    447
    +0.11
    0.5%
    378
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    43
    +0.12
    0.05
    297
    +0.11
    0.04
    100
    +0.10
    0.04
    Negative Logits
    staking
    -0.81
     guiActiveUn
    -0.73
    inction
    -0.73
    atively
    -0.73
    banks
    -0.72
    ļéĨĴ
    -0.69
    conom
    -0.69
    etary
    -0.69
    abase
    -0.66
    eatures
    -0.66
    POSITIVE LOGITS
     sir
    1.28
     please
    1.05
     huh
    1.04
     dear
    1.02
     gentlemen
    0.96
     amen
    0.93
     mate
    0.88
     darling
    0.86
     ladies
    0.85
     buddy
    0.85
    Activations Density 0.335%

    No Known Activations