© 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. 8826
    Prev
    Next
    INDEX
    Explanations

    sports-related terms, team names, and competition results

    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
    633
    +0.09
    0.4%
    556
    +0.09
    0.4%
    99
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.09
    0.04
    232
    +0.09
    0.04
    103
    +0.09
    0.03
    Negative Logits
    è£ħ
    -0.69
    lectic
    -0.68
    tumblr
    -0.65
     AMA
    -0.61
    frame
    -0.59
     Recording
    -0.58
     Ramirez
    -0.57
    hetti
    -0.57
     DOI
    -0.57
     matrix
    -0.57
    POSITIVE LOGITS
     Lauder
    0.84
    ilda
    0.83
    eus
    0.68
    leon
    0.68
    liction
    0.65
    of
    0.65
     faire
    0.65
    cially
    0.64
    ikh
    0.64
    olph
    0.63
    Activations Density 0.154%

    No Known Activations