© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1451
    Prev
    Next
    INDEX
    Explanations

    patterns related to HTML coding structure

    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
    373
    +0.14
    0.6%
    160
    +0.12
    0.5%
    385
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    653
    +0.14
    0.02
    617
    +0.12
    0.02
    160
    +0.10
    0.02
    Negative Logits
    ModLoader
    -0.74
    ãĥ£
    -0.72
     somew
    -0.67
     uncond
    -0.67
     fortun
    -0.66
     Travels
    -0.64
     bitters
    -0.64
     derog
    -0.63
     Awakens
    -0.63
     Ukrain
    -0.61
    POSITIVE LOGITS
    img
    1.22
    !--
    1.17
    span
    1.08
    meta
    0.97
    div
    0.93
    input
    0.92
    iframe
    0.91
    html
    0.86
    br
    0.85
    TABLE
    0.81
    Activations Density 0.008%

    No Known Activations