© 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. 1499
    Prev
    Next
    INDEX
    Explanations

    prominent events or statements that have significant social or political implications

    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
    608
    +0.13
    0.6%
    195
    +0.11
    0.5%
    646
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    646
    +0.13
    0.03
    608
    +0.11
    0.04
    195
    +0.10
    0.02
    Negative Logits
    mate
    -0.68
     route
    -0.66
    treated
    -0.65
    atum
    -0.65
    ighth
    -0.64
    ./
    -0.63
    parent
    -0.63
    uded
    -0.62
    sm
    -0.61
    ta
    -0.61
    POSITIVE LOGITS
     outcry
    0.95
     applause
    0.91
     speculation
    0.90
     laughter
    0.88
     ire
    0.84
     widespread
    0.83
     prompt
    0.83
     inquiries
    0.82
     cheers
    0.81
     controversy
    0.81
    Activations Density 0.103%

    No Known Activations