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. 1494
    Prev
    Next
    INDEX
    Explanations

    words related to giving praise or criticism

    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
    +0.16
    0.7%
    314
    +0.15
    0.7%
    675
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    675
    +0.16
    0.12
    6
    +0.15
    0.11
    504
    +0.11
    0.09
    Negative Logits
     incorpor
    -0.90
     ende
    -0.84
     obser
    -0.82
     secretaries
    -0.81
     mushroom
    -0.77
     controvers
    -0.75
     incent
    -0.74
     ponder
    -0.73
     warr
    -0.72
     perspect
    -0.72
    POSITIVE LOGITS
    ï¸ı
    1.33
    ¯
    1.03
    °
    1.01
    âĻ
    1.01
    ï¸
    0.98
    é¾į
    0.94
    ÃĽ
    0.94
    âϦ
    0.91
    âĿ
    0.88
    âĶĢâĶĢâĶĢâĶĢ
    0.88
    Activations Density 0.369%

    No Known Activations