© 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 12288
    5. 8-RES_FS12288-JB
    6. 10823
    Prev
    Next
    INDEX
    Explanations

    information related to sporting events and competitions, particularly focusing on races, results, and competitors

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs12288-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_12288
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    12,288
    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
    346
    +0.11
    0.5%
    94
    +0.09
    0.4%
    459
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.11
    0.05
    281
    +0.09
    0.04
    412
    +0.09
    0.04
    Negative Logits
    soType
    -0.95
    FBI
    -0.88
    agency
    -0.82
     distrust
    -0.79
     Manafort
    -0.78
     intrusive
    -0.77
    politics
    -0.76
     Detect
    -0.75
    monitor
    -0.73
    Crime
    -0.73
    POSITIVE LOGITS
     runner
    1.18
     finals
    1.05
     runners
    1.04
     winner
    1.04
     unbeaten
    1.02
     medal
    1.01
     solo
    1.01
     feat
    0.99
     undefeated
    0.99
     contestant
    0.99
    Activations Density 1.041%

    No Known Activations