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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 947
    Prev
    Next
    INDEX
    Explanations

    products, items, and tools commonly associated with cleaning and household maintenance

    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
    742
    +0.12
    0.6%
    116
    +0.12
    0.5%
    285
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.13
    742
    +0.12
    0.08
    116
    +0.11
    0.07
    Negative Logits
    Ĥª
    -0.69
     Subtle
    -0.67
    ãĥ¯ãĥ³
    -0.66
     stoked
    -0.61
     shattering
    -0.59
     backdrop
    -0.59
     spirited
    -0.59
    ãĥ¼ãĥĨãĤ£
    -0.57
    âĦ¢:
    -0.56
    chell
    -0.56
    POSITIVE LOGITS
    ongevity
    1.27
    yrics
    1.26
    ateral
    1.24
    ifestyle
    1.23
    ibrarian
    1.21
    uggage
    1.19
    ayers
    1.15
    adders
    1.14
    ifest
    1.14
    aptop
    1.14
    Activations Density 1.822%

    No Known Activations