© 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. 12157
    Prev
    Next
    INDEX
    Explanations

    dates and numbers with special meanings

    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
    590
    +0.10
    0.4%
    24
    +0.10
    0.4%
    430
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    744
    +0.10
    0.02
    141
    +0.10
    0.02
    24
    +0.10
    0.02
    Negative Logits
    matically
    -0.74
    acebook
    -0.72
    asers
    -0.71
    owler
    -0.64
     smugglers
    -0.62
    avorite
    -0.61
     contention
    -0.61
     overd
    -0.59
    lly
    -0.59
    enta
    -0.59
    POSITIVE LOGITS
     partName
    1.00
     Became
    0.97
     RELEASE
    0.92
     GMT
    0.81
     Added
    0.80
     Updated
    0.79
     Coffin
    0.79
     Apply
    0.75
     Converted
    0.71
     EDIT
    0.69
    Activations Density 0.042%

    No Known Activations