© 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. 11912
    Prev
    Next
    INDEX
    Explanations

    names or terms related to sports teams or events

    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
    642
    +0.14
    0.7%
    274
    +0.12
    0.6%
    134
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.02
    628
    +0.12
    0.02
    326
    +0.11
    0.02
    Negative Logits
    culosis
    -0.88
    nell
    -0.84
    ergy
    -0.75
    20439
    -0.73
    edo
    -0.73
    gling
    -0.73
    ogy
    -0.73
    licks
    -0.72
    ledge
    -0.72
    iless
    -0.71
    POSITIVE LOGITS
    acs
    1.04
    iah
    0.91
     Stam
    0.83
    acco
    0.79
    abeth
    0.77
    aqu
    0.76
     Cohn
    0.69
    án
    0.68
    achi
    0.68
     Ys
    0.67
    Activations Density 0.054%

    No Known Activations