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 24576
    5. 8-RES_FS24576-JB
    6. 10939
    Prev
    Next
    INDEX
    Explanations

    Japanese names, specifically the name "Yas" or variations of it

    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
    284
    +0.12
    0.5%
    167
    +0.11
    0.5%
    48
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    284
    +0.11
    0.02
    659
    +0.10
    0.02
    Negative Logits
    arity
    -0.79
     Belg
    -0.62
    ATIVE
    -0.61
     Weasley
    -0.59
     helium
    -0.58
     Vaugh
    -0.58
     prope
    -0.57
    mble
    -0.57
    lly
    -0.57
    agents
    -0.56
    POSITIVE LOGITS
    é»Ĵ
    0.87
    sin
    0.76
    cano
    0.75
    ienced
    0.71
    ols
    0.71
    aniel
    0.71
    aez
    0.70
    anta
    0.70
    lot
    0.69
    opard
    0.69
    Activations Density 0.054%

    No Known Activations