© 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. 8631
    Prev
    Next
    INDEX
    Explanations

    instances of the word "its" paired with a following adjective or noun

    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
    608
    +0.10
    0.5%
    758
    +0.09
    0.4%
    605
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    758
    +0.10
    0.03
    562
    +0.09
    0.03
    608
    +0.09
    0.03
    Negative Logits
     thereby
    -0.66
     [];
    -0.65
    ufact
    -0.63
    >>\
    -0.59
    duction
    -0.59
    conom
    -0.59
     Recomm
    -0.59
    Transfer
    -0.58
    ocument
    -0.58
    rehens
    -0.58
    POSITIVE LOGITS
     own
    1.31
     sights
    1.20
     doubts
    1.00
     detractors
    0.93
     fingerprints
    0.91
     tentacles
    0.83
     faults
    0.79
     feet
    0.78
     patented
    0.77
     strongest
    0.76
    Activations Density 0.073%

    No Known Activations