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 49152
    5. 8-RES_FS49152-JB
    6. 26216
    Prev
    Next
    INDEX
    Explanations

    mentions of libraries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    26
    +0.13
    0.6%
    288
    +0.12
    0.6%
    11
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    26
    +0.13
    0.02
    11
    +0.12
    0.01
    211
    +0.12
    0.01
    Negative Logits
    engeance
    -0.62
     believer
    -0.62
    akening
    -0.61
    assis
    -0.61
    lers
    -0.61
    elin
    -0.61
    ushima
    -0.60
     Samoa
    -0.60
    ĪĴ
    -0.60
    killed
    -0.59
    POSITIVE LOGITS
    ibrarian
    0.91
     shelves
    0.85
    pedia
    0.79
    artment
    0.78
    ãĥ´ãĤ¡
    0.73
    ibrary
    0.72
     scrolls
    0.71
    mage
    0.71
    sonian
    0.70
     dumps
    0.69
    Activations Density 0.009%

    No Known Activations