© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 20134
    Prev
    Next
    INDEX
    Explanations

    verbs related to sports actions like scoring, lifting, rallying, beating, claiming, booking, conceding, converting, putting, drawing, getting, tying, giving, allowing, knocking, and launching

    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
    468
    +0.12
    0.6%
    603
    +0.10
    0.5%
    668
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    533
    +0.12
    0.05
    183
    +0.10
    0.04
    282
    +0.10
    0.04
    Negative Logits
    DragonMagazine
    -0.88
    pmwiki
    -0.83
    Ingredients
    -0.73
    20439
    -0.72
    catentry
    -0.71
    Scale
    -0.69
     newsletters
    -0.65
     curric
    -0.65
     *)
    -0.64
    TeX
    -0.63
    POSITIVE LOGITS
     himself
    0.97
     teammates
    0.85
     runners
    0.85
     opponents
    0.84
     teammate
    0.84
     unbeaten
    0.84
    wered
    0.84
     clutch
    0.82
     rebounds
    0.78
     halftime
    0.78
    Activations Density 0.202%

    No Known Activations