© 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. 9543
    Prev
    Next
    INDEX
    Explanations

    athletic activities and sports-related terms

    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
    701
    +0.12
    0.5%
    385
    +0.11
    0.5%
    289
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    701
    +0.12
    0.03
    659
    +0.11
    0.03
    289
    +0.11
    0.01
    Negative Logits
     Reloaded
    -0.72
     shorth
    -0.71
     Wizard
    -0.63
     Vega
    -0.60
     Goff
    -0.59
     Sounders
    -0.59
     Sahara
    -0.59
     FANTASY
    -0.58
     mosaic
    -0.58
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.58
    POSITIVE LOGITS
    ouse
    1.26
    urst
    1.25
    lete
    1.17
    aniel
    1.11
    ulhu
    1.08
    reshold
    1.02
    ouses
    1.02
    opter
    0.99
    orned
    0.97
    sburg
    0.95
    Activations Density 0.078%

    No Known Activations