© 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. 11991
    Prev
    Next
    INDEX
    Explanations

    phrases related to work tasks and positions

    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
    665
    +0.12
    0.5%
    658
    +0.11
    0.5%
    373
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    665
    +0.12
    0.07
    761
    +0.11
    0.04
    587
    +0.09
    0.04
    Negative Logits
    catentry
    -0.93
    inventoryQuantity
    -0.91
    quickShipAvailable
    -0.80
     hesitate
    -0.73
    itiveness
    -0.72
    NetMessage
    -0.71
    isSpecialOrderable
    -0.69
     Flavoring
    -0.68
    theless
    -0.68
    ylon
    -0.67
    POSITIVE LOGITS
     theirs
    0.75
     their
    0.69
     unpaid
    0.65
    ITE
    0.63
    study
    0.62
     his
    0.62
    ezvous
    0.61
     THEIR
    0.60
     Clancy
    0.60
    heed
    0.60
    Activations Density 0.337%

    No Known Activations