© 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. 12076
    Prev
    Next
    INDEX
    Explanations

    common nouns

    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
    447
    +0.27
    1.3%
    480
    +0.26
    1.2%
    87
    +0.15
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.27
    0.04
    464
    +0.26
    0.05
    480
    +0.15
    0.01
    Negative Logits
    assies
    -0.83
     Jagu
    -0.76
    Ire
    -0.75
    bledon
    -0.71
     cabinets
    -0.68
     Oval
    -0.67
    drops
    -0.66
    DAQ
    -0.64
    elines
    -0.64
     Seym
    -0.64
    POSITIVE LOGITS
     ·
    0.79
     ])
    0.63
     variant
    0.62
     transcript
    0.62
     )))
    0.61
     !
    0.60
    igmatic
    0.60
     ..........
    0.59
     ][
    0.59
     )]
    0.59
    Activations Density 0.189%

    No Known Activations