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. 21514
    Prev
    Next
    INDEX
    Explanations

    language related to regulations, compliance, and permissions

    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
    694
    +0.11
    0.5%
    447
    +0.10
    0.5%
    516
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    300
    +0.11
    0.06
    516
    +0.10
    0.04
    661
    +0.10
    0.03
    Negative Logits
    lez
    -0.79
    ãĤ§
    -0.77
    Dust
    -0.71
    jab
    -0.67
    ruary
    -0.67
    Throw
    -0.66
     Roller
    -0.66
     whirlwind
    -0.65
     lol
    -0.64
     ));
    -0.64
    POSITIVE LOGITS
     lawfully
    1.22
     specified
    1.15
     deemed
    1.10
     medically
    0.99
     expressly
    0.97
     pursuant
    0.95
     accompanied
    0.93
     complying
    0.93
     reasonably
    0.92
     designated
    0.92
    Activations Density 0.265%

    No Known Activations