© 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. 8499
    Prev
    Next
    INDEX
    Explanations

    verbs related to capability and possibility

    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
    480
    +0.48
    2.5%
    87
    +0.18
    1.0%
    447
    +0.16
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.48
    0.03
    266
    +0.18
    0.09
    671
    +0.16
    0.05
    Negative Logits
    rather
    -0.57
     redes
    -0.54
    eday
    -0.51
    almost
    -0.49
     Ezek
    -0.49
    anwhile
    -0.48
    okingly
    -0.48
    oso
    -0.47
     respectively
    -0.47
     culminating
    -0.47
    POSITIVE LOGITS
     anymore
    1.59
     nor
    1.49
     whatsoever
    0.91
     anything
    0.88
     any
    0.87
    yet
    0.86
     slightest
    0.85
    nor
    0.83
     anywhere
    0.83
     anybody
    0.78
    Activations Density 0.810%

    No Known Activations