© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11013
    Prev
    Next
    INDEX
    Explanations

    information about upcoming events, news, and studies

    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
    726
    +0.11
    0.5%
    687
    +0.11
    0.5%
    402
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    687
    +0.11
    0.03
    402
    +0.11
    0.03
    726
    +0.10
    0.03
    Negative Logits
    Enlarge
    -0.85
    DragonMagazine
    -0.79
    adr
    -0.79
    xtap
    -0.78
    pload
    -0.77
    ader
    -0.75
    Cro
    -0.72
    oder
    -0.71
    ococ
    -0.69
    Disk
    -0.68
    POSITIVE LOGITS
     information
    1.03
     info
    1.02
     than
    0.97
     details
    0.97
     detailed
    0.87
     insight
    0.85
     interesting
    0.83
     ado
    0.82
     informative
    0.81
     exciting
    0.81
    Activations Density 0.032%

    No Known Activations