© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 19799
    Prev
    Next
    INDEX
    Explanations

    data related to sports teams, rankings, and statistics

    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
    393
    +0.10
    0.5%
    50
    +0.09
    0.4%
    289
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    176
    +0.10
    0.03
    570
    +0.09
    0.02
    711
    +0.09
    0.02
    Negative Logits
    enhagen
    -0.63
    ournal
    -0.60
    owship
    -0.58
     Spiel
    -0.57
     ãĤµ
    -0.56
    afety
    -0.56
    anners
    -0.54
     Sins
    -0.52
    zhou
    -0.52
    ibal
    -0.51
    POSITIVE LOGITS
    azo
    0.73
    achev
    0.65
    ĵĺ
    0.63
     scissors
    0.57
     ignition
    0.56
     turret
    0.56
     punch
    0.55
     magnification
    0.55
    uple
    0.55
     Gujar
    0.55
    Activations Density 0.342%

    No Known Activations