© 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 49152
    9. 8-RES_FS49152-JB
    11. 41522
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "to be" in various forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    102
    +0.12
    0.5%
    55
    +0.11
    0.5%
    556
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    55
    +0.12
    0.03
    102
    +0.11
    0.03
    449
    +0.10
    0.02
    Negative Logits
    requ
    -0.69
     Wrap
    -0.68
     Supplemental
    -0.68
    framework
    -0.67
     cancellation
    -0.66
     externalToEVAOnly
    -0.66
    ooters
    -0.65
    iation
    -0.64
     Candle
    -0.63
    vity
    -0.62
    POSITIVE LOGITS
     responsible
    0.95
     footing
    0.88
     infiltrated
    0.86
    afort
    0.83
     accountable
    0.83
     willing
    0.82
     weakest
    0.79
     benefited
    0.79
     inhab
    0.77
     controlling
    0.77
    Activations Density 0.038%

    No Known Activations