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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 554
    Prev
    Next
    INDEX
    Explanations

    terms related to spirituality, Indian philosophy, and medical treatments

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs1536-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_1536
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    1,536
    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
    +0.12
    0.5%
    699
    +0.11
    0.5%
    291
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.10
    326
    +0.11
    0.11
    699
    +0.11
    0.07
    Negative Logits
    ional
    -0.82
    ually
    -0.75
    IBLE
    -0.73
    ivity
    -0.73
    IFIED
    -0.72
    ajor
    -0.71
    icably
    -0.71
    arians
    -0.70
    iveness
    -0.70
    atform
    -0.70
    POSITIVE LOGITS
    mph
    1.07
    nergy
    1.06
    lene
    1.05
    outube
    0.98
    eah
    0.97
    gdala
    0.97
    ng
    0.93
    rics
    0.93
    gian
    0.92
    stal
    0.92
    Activations Density 2.219%

    No Known Activations