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. 2144
    Prev
    Next
    INDEX
    Explanations

    information about professional athletes and their careers

    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
    603
    +0.14
    0.6%
    373
    +0.14
    0.6%
    505
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    603
    +0.14
    0.10
    412
    +0.14
    0.09
    422
    +0.11
    0.07
    Negative Logits
    Plan
    -0.75
    resist
    -0.74
     Canaver
    -0.71
    aminer
    -0.68
    uble
    -0.66
    valid
    -0.65
    qs
    -0.65
     assumptions
    -0.65
     Rowling
    -0.64
    Acknowled
    -0.63
    POSITIVE LOGITS
     Rookie
    1.28
     league
    1.17
     fullback
    1.15
     AHL
    1.14
     postseason
    1.09
     preseason
    1.08
     rookie
    1.08
     NCAA
    1.07
     teammates
    1.06
     Championship
    1.06
    Activations Density 2.030%

    No Known Activations