© 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. 12142
    Prev
    Next
    INDEX
    Explanations

    words related to concepts in science, specifically astronomy, and potentially terms related to international trade and political issues

    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
    373
    +0.16
    0.8%
    450
    +0.11
    0.5%
    311
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    373
    +0.16
    -0.02
    232
    +0.11
    0.04
    406
    +0.10
    0.04
    Negative Logits
     è£ı
    -0.65
     cig
    -0.64
     dime
    -0.63
     Cadillac
    -0.63
     respectively
    -0.61
     warr
    -0.61
     tremend
    -0.60
     legion
    -0.60
    >]
    -0.60
    *.
    -0.60
    POSITIVE LOGITS
    itably
    0.99
    inarily
    0.96
    atically
    0.95
    ations
    0.92
    hetically
    0.91
    ating
    0.90
    itionally
    0.89
    ologists
    0.88
    ational
    0.87
    ices
    0.87
    Activations Density 0.153%

    No Known Activations