© 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. 10581
    Prev
    Next
    INDEX
    Explanations

    professional sports teams along with associated statistics and player names

    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
    454
    +0.11
    0.5%
    602
    +0.10
    0.4%
    686
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.11
    0.05
    656
    +0.10
    0.04
    201
    +0.09
    0.04
    Negative Logits
    enegger
    -1.07
    schild
    -1.06
    ngth
    -0.79
    nces
    -0.75
    olkien
    -0.74
    aird
    -0.73
    adj
    -0.73
    trigger
    -0.73
    recy
    -0.73
    ibliography
    -0.73
    POSITIVE LOGITS
     Eagles
    1.13
     Falcons
    1.12
     Giants
    1.11
     Buccaneers
    1.10
     Chiefs
    1.09
     Jets
    1.08
     Cardinals
    1.05
     Royals
    1.05
     Wolves
    1.04
     Bears
    1.03
    Activations Density 0.149%

    No Known Activations