© 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. 9015
    Prev
    Next
    INDEX
    Explanations

    keywords related to SEO, link building, and website content

    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
    13
    +0.11
    0.5%
    225
    +0.10
    0.5%
    679
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.11
    0.04
    225
    +0.10
    0.04
    641
    +0.10
    0.03
    Negative Logits
    llah
    -0.90
     Presbyter
    -0.79
    hani
    -0.76
    lain
    -0.75
    itary
    -0.74
    ICLE
    -0.68
     Rept
    -0.68
     Alz
    -0.67
     surviving
    -0.67
    ridge
    -0.67
    POSITIVE LOGITS
     SEO
    1.18
     Marketing
    1.06
     marketing
    1.06
     marketers
    1.04
     optimization
    1.03
     analytics
    1.00
    Market
    0.99
     monet
    0.98
    Commerce
    0.96
     influ
    0.91
    Activations Density 0.149%

    No Known Activations