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. 1126
    Prev
    Next
    INDEX
    Explanations

    information related to education, political activities, and city governance

    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
    480
    +0.51
    3.2%
    447
    +0.39
    2.4%
    87
    +0.22
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    480
    +0.51
    0.10
    266
    +0.39
    0.31
    101
    +0.22
    0.26
    Negative Logits
     versa
    -0.58
    *.
    -0.56
    ļéĨĴ
    -0.53
     theirs
    -0.52
    _.
    -0.51
     thereof
    -0.51
    ccess
    -0.51
     accordingly
    -0.50
     eleph
    -0.50
    anwhile
    -0.50
    POSITIVE LOGITS
     Houth
    0.58
     OnePlus
    0.57
     Rohingya
    0.54
     Hubble
    0.53
     Canaver
    0.53
     SpaceX
    0.52
     Xperia
    0.52
     Orioles
    0.51
     Xiaomi
    0.50
     Corbyn
    0.50
    Activations Density 9.203%

    No Known Activations