© 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 24576
    9. 8-RES_FS24576-JB
    11. 1841
    Prev
    Next
    INDEX
    Explanations

    phrases related to historical events, individuals, and locations

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    674
    +0.11
    0.5%
    645
    +0.09
    0.4%
    178
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    720
    +0.11
    0.05
    546
    +0.09
    0.04
    178
    +0.09
    0.05
    Negative Logits
     Travels
    -0.91
    hov
    -0.65
     intersect
    -0.64
    issance
    -0.64
    yssey
    -0.64
     overflow
    -0.63
    reetings
    -0.62
     multimedia
    -0.62
    rology
    -0.61
    amorph
    -0.61
    POSITIVE LOGITS
     preferring
    1.47
     citing
    1.34
     fearing
    1.25
     stating
    1.10
     insisting
    1.05
     believing
    1.03
     opting
    1.01
     saying
    0.99
     vehemently
    0.96
     arguing
    0.96
    Activations Density 0.371%

    No Known Activations