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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 1536
    5. 8-RES_FS1536-JB
    6. 666
    Prev
    Next
    INDEX
    Explanations

    past and present participles used as descriptors

    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
    102
    +0.15
    0.7%
    566
    +0.14
    0.6%
    55
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    102
    +0.15
    0.13
    55
    +0.14
    0.13
    566
    +0.12
    0.11
    Negative Logits
    lies
    -0.77
     Relief
    -0.71
    Must
    -0.69
    izable
    -0.68
     Needs
    -0.68
    ives
    -0.64
    rones
    -0.63
    terday
    -0.63
    warts
    -0.62
     Solution
    -0.62
    POSITIVE LOGITS
     subjected
    1.03
     criticized
    0.99
     likened
    0.98
     replaced
    0.94
     unable
    0.92
     able
    0.92
    avering
    0.91
     taken
    0.91
     criticised
    0.90
    cffffcc
    0.89
    Activations Density 0.799%

    No Known Activations