Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 23432
    Prev
    Next
    INDEX
    Explanations

    references to HTML and web development concepts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    167
    +0.11
    0.5%
    57
    +0.11
    0.5%
    680
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.11
    0.01
    289
    +0.11
    0.01
    57
    +0.10
    0.01
    Negative Logits
    alties
    -0.96
    lain
    -0.95
    alty
    -0.81
    女
    -0.76
    wcs
    -0.74
    isky
    -0.73
    ndra
    -0.72
    cession
    -0.71
    esses
    -0.68
    stown
    -0.67
    POSITIVE LOGITS
     markup
    0.93
    HTML
    0.85
    Parser
    0.79
    Content
    0.79
    Assembly
    0.78
    Lua
    0.78
    special
    0.75
    uration
    0.74
     tags
    0.74
     TEXT
    0.73
    Activations Density 0.032%

    No Known Activations