© 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. 19671
    Prev
    Next
    INDEX
    Explanations

    references to digital media phenomena like GIFs and internet memes

    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
    393
    +0.11
    0.5%
    608
    +0.11
    0.5%
    730
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.06
    362
    +0.11
    0.05
    669
    +0.10
    0.04
    Negative Logits
    cade
    -0.72
    fur
    -0.72
    maps
    -0.71
    pots
    -0.69
     Unsure
    -0.69
    bats
    -0.68
    daq
    -0.67
    ©¶æ¥µ
    -0.67
    notations
    -0.67
    arnaev
    -0.66
    POSITIVE LOGITS
     sorts
    1.37
     desperation
    1.10
     ignorance
    1.08
     stupidity
    0.95
     coward
    0.92
     humanity
    0.91
     imagination
    0.89
     folly
    0.89
     colonialism
    0.88
     laz
    0.87
    Activations Density 0.243%

    No Known Activations