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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 870
    Prev
    Next
    INDEX
    Explanations

    instances of mentions related to same-sex marriage, including discussions, legal cases, and societal viewpoints

    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
    288
    +0.12
    0.5%
    224
    +0.11
    0.5%
    524
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    524
    +0.12
    0.02
    444
    +0.11
    0.02
    557
    +0.11
    0.02
    Negative Logits
     tremend
    -0.72
    UME
    -0.71
    ngth
    -0.67
    DragonMagazine
    -0.67
    Reviewer
    -0.66
    erva
    -0.66
    oola
    -0.66
    aceae
    -0.64
     Indust
    -0.63
    herty
    -0.63
    POSITIVE LOGITS
     equality
    1.24
     bans
    0.99
     Equality
    0.94
    equality
    0.93
     rights
    0.92
     legalization
    0.90
     marriage
    0.88
     marry
    0.87
     repeal
    0.86
     polygamy
    0.85
    Activations Density 0.032%

    No Known Activations