© 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. 10669
    Prev
    Next
    INDEX
    Explanations

    references to sports teams, players, and events

    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
    393
    +0.15
    0.7%
    362
    +0.15
    0.7%
    636
    +0.14
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    362
    +0.15
    0.12
    636
    +0.15
    0.09
    608
    +0.14
    0.10
    Negative Logits
    pers
    -0.78
    scape
    -0.75
    chu
    -0.71
    finding
    -0.71
    hari
    -0.70
    bourg
    -0.69
    SPONSORED
    -0.69
    heit
    -0.68
    arya
    -0.68
    tle
    -0.67
    POSITIVE LOGITS
     playoffs
    1.22
     league
    1.18
     latter
    1.12
     aforementioned
    1.10
     postseason
    1.09
     offseason
    1.03
     Bulldogs
    1.02
     dreaded
    1.01
     same
    1.00
     likes
    0.99
    Activations Density 0.441%

    No Known Activations