© 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. 2199
    Prev
    Next
    INDEX
    Explanations

    sports-related terms and names, particularly in the context of basketball teams and competitions

    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
    4
    +0.13
    0.6%
    364
    +0.10
    0.5%
    620
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.13
    0.08
    364
    +0.10
    0.05
    4
    +0.10
    0.05
    Negative Logits
    ratom
    -0.73
    duty
    -0.71
    ourning
    -0.70
    riel
    -0.69
    utics
    -0.65
    govtrack
    -0.64
    dain
    -0.64
    é¾įåĸļ士
    -0.63
    asionally
    -0.62
    tesy
    -0.62
    POSITIVE LOGITS
     debacle
    0.85
     fiasco
    0.83
     equivalent
    0.77
     playbook
    0.75
     version
    0.69
     consortium
    0.68
     variety
    0.66
     trio
    0.65
     counterpart
    0.65
     triangle
    0.64
    Activations Density 0.420%

    No Known Activations