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 24576
    5. 8-RES_FS24576-JB
    6. 8324
    Prev
    Next
    INDEX
    Explanations

    Biblical references and teachings

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs24576-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_24576
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    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
    325
    +0.12
    0.6%
    208
    +0.11
    0.5%
    18
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    6
    +0.12
    0.03
    325
    +0.11
    0.03
    18
    +0.10
    0.03
    Negative Logits
     loyal
    -0.67
    Desktop
    -0.62
     scrut
    -0.59
     steady
    -0.58
     disposable
    -0.57
     Bench
    -0.57
     tut
    -0.56
     household
    -0.55
     hygiene
    -0.54
     stead
    -0.54
    POSITIVE LOGITS
     ff
    1.01
     âĨij
    0.96
     NRS
    0.87
     seq
    0.87
    ff
    0.85
     DOI
    0.82
     quoting
    0.82
     istg
    0.79
     .)
    0.79
    .;
    0.78
    Activations Density 0.068%

    No Known Activations