Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 1072
    Prev
    Next
    INDEX
    Explanations

    violent actions such as punching, stabbing, or assault

    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
    553
    +0.11
    0.5%
    282
    +0.10
    0.4%
    468
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    686
    +0.11
    0.04
    553
    +0.10
    0.04
    468
    +0.09
    0.04
    Negative Logits
    stellar
    -0.77
     spons
    -0.75
     redes
    -0.71
    soDeliveryDate
    -0.70
    DragonMagazine
    -0.68
    isoft
    -0.66
    Climate
    -0.65
    amins
    -0.63
    natureconservancy
    -0.62
     Insider
    -0.62
    POSITIVE LOGITS
     him
    1.01
     someone
    0.90
     somebody
    0.85
     bystanders
    0.84
     them
    0.82
    someone
    0.78
     awa
    0.77
     himself
    0.76
    ched
    0.74
    bery
    0.73
    Activations Density 0.134%

    No Known Activations