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. 769
    Prev
    Next
    INDEX
    Explanations

    personal possessive pronouns, "yours" and "ours"

    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
    35
    +0.14
    0.6%
    526
    +0.10
    0.5%
    497
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    35
    +0.14
    0.01
    366
    +0.10
    0.01
    685
    +0.10
    0.01
    Negative Logits
     Beg
    -0.69
     IPM
    -0.66
    hips
    -0.64
    edd
    -0.64
    orsi
    -0.63
    itement
    -0.62
    atever
    -0.62
    establishment
    -0.62
    ypes
    -0.61
    iencies
    -0.60
    POSITIVE LOGITS
    selves
    1.12
    self
    1.07
    craft
    0.87
    field
    0.76
    fields
    0.74
    creen
    0.72
    opia
    0.72
    !/
    0.72
    cart
    0.71
    ovie
    0.69
    Activations Density 0.016%

    No Known Activations