© 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. 10677
    Prev
    Next
    INDEX
    Explanations

    references to the news organization Breitbart

    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
    +0.11
    0.5%
    420
    +0.11
    0.5%
    651
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.05
    326
    +0.11
    0.04
    343
    +0.11
    0.03
    Negative Logits
    phis
    -0.95
    mble
    -0.86
    erve
    -0.81
    oeuv
    -0.79
    daq
    -0.79
    alogue
    -0.77
    essage
    -0.76
    ube
    -0.74
    iven
    -0.73
    istance
    -0.73
    POSITIVE LOGITS
    FILE
    0.67
    olds
    0.66
    NEWS
    0.65
    URN
    0.61
     ahead
    0.60
    ORN
    0.59
     Mage
    0.59
     Bunker
    0.58
    shi
    0.58
    iances
    0.57
    Activations Density 0.208%

    No Known Activations