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. 2808
    Prev
    Next
    INDEX
    Explanations

    verbs related to success and opportunity

    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
    490
    +0.13
    0.6%
    650
    +0.12
    0.6%
    262
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    490
    +0.13
    0.10
    650
    +0.12
    0.11
    298
    +0.11
    0.08
    Negative Logits
     Donation
    -0.68
    ettings
    -0.64
    pecially
    -0.60
    isky
    -0.60
    racuse
    -0.59
    pton
    -0.59
    heid
    -0.58
    arta
    -0.58
     Annotations
    -0.57
     Sins
    -0.57
    POSITIVE LOGITS
     fruition
    1.08
     happening
    0.83
     occurring
    0.74
     reverber
    0.71
     prevail
    0.70
     tires
    0.69
     resurgence
    0.69
     manifested
    0.68
     haunt
    0.68
     unchecked
    0.66
    Activations Density 2.412%

    No Known Activations