© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10096
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to accommodations and services

    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
    447
    +0.31
    1.5%
    481
    +0.26
    1.3%
    105
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.31
    0.13
    647
    +0.26
    0.07
    665
    +0.09
    0.09
    Negative Logits
    quit
    -0.72
    Leary
    -0.71
    elo
    -0.69
    ildo
    -0.65
    Copyright
    -0.65
    don
    -0.64
    nob
    -0.63
    Thumbnail
    -0.63
    Evil
    -0.62
    thing
    -0.61
    POSITIVE LOGITS
     numerous
    1.09
     several
    0.99
     myriad
    0.95
     various
    0.94
     extensive
    0.92
     diverse
    0.85
     varied
    0.84
     innumerable
    0.81
     considerable
    0.79
     assorted
    0.77
    Activations Density 1.406%

    No Known Activations