© 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 12288
    9. 8-RES_FS12288-JB
    11. 10858
    Prev
    Next
    INDEX
    Explanations

    sports-related content, including football plays and game descriptions

    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
    481
    +0.61
    4.7%
    373
    +0.22
    1.7%
    157
    +0.06
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.61
    0.20
    373
    +0.22
    -0.15
    470
    +0.06
    0.02
    Negative Logits
    ]."
    -0.57
    )."
    -0.56
    .).
    -0.55
    }.
    -0.54
    !".
    -0.53
    .ãĢį
    -0.50
    ".[
    -0.50
    )).
    -0.50
    ).[
    -0.50
    ".
    -0.49
    POSITIVE LOGITS
     meanwhile
    0.37
    resa
    0.35
    ':
    0.32
    gary
    0.30
    inarily
    0.30
    surprisingly
    0.30
     spokeswoman
    0.29
     Canaver
    0.29
     Bernstein
    0.28
    ideshow
    0.28
    Activations Density 5.630%

    No Known Activations