© 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. 12402
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to technology companies or products

    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
    +0.22
    1.0%
    481
    +0.13
    0.6%
    659
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.22
    0.07
    722
    +0.13
    0.04
    232
    +0.12
    0.04
    Negative Logits
    20439
    -0.70
    ],"
    -0.65
     Guant
    -0.62
    ::::::::
    -0.59
    ãĥķãĤ¡
    -0.58
    PsyNetMessage
    -0.57
    ;;;;;;;;;;;;
    -0.56
    geries
    -0.55
    ãĤ°
    -0.55
     Bron
    -0.54
    POSITIVE LOGITS
    sequently
    0.86
     also
    0.86
    ogether
    0.83
     furthermore
    0.79
     meanwhile
    0.79
     however
    0.77
     specializes
    0.75
     assures
    0.75
     therefore
    0.74
    hetically
    0.72
    Activations Density 0.200%

    No Known Activations