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 3072
    5. 8-RES_FS3072-JB
    6. 2146
    Prev
    Next
    INDEX
    Explanations

    words related to physical challenges, competition, and conflict

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs3072-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_3072
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    3,072
    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
    192
    +0.10
    0.4%
    298
    +0.09
    0.4%
    88
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.10
    0.15
    298
    +0.09
    0.09
    146
    +0.09
    0.08
    Negative Logits
    PDATED
    -0.68
     Recipes
    -0.65
    soDeliveryDate
    -0.65
    ename
    -0.65
     addresses
    -0.64
    Chart
    -0.64
    aughtered
    -0.63
    Asset
    -0.62
    ived
    -0.61
     Pric
    -0.60
    POSITIVE LOGITS
     onslaught
    1.17
     encro
    1.05
     invaders
    1.00
     invading
    0.96
     adversity
    0.91
     intruder
    0.90
     pesky
    0.89
     backdrop
    0.89
     wrath
    0.87
     obstacles
    0.86
    Activations Density 2.975%

    No Known Activations