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. 19281
    Prev
    Next
    INDEX
    Explanations

    phrases related to the passing of laws or legislation

    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
    608
    +0.11
    0.5%
    218
    +0.11
    0.5%
    764
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    608
    +0.11
    0.04
    764
    +0.11
    0.03
    123
    +0.10
    0.04
    Negative Logits
    zai
    -0.90
    entimes
    -0.76
    idas
    -0.74
    geist
    -0.71
    hop
    -0.69
    die
    -0.68
    frog
    -0.66
    gang
    -0.65
    cies
    -0.64
    yip
    -0.62
    POSITIVE LOGITS
     adulthood
    1.04
     existence
    0.76
     orbit
    0.74
    jected
    0.71
     ob
    0.69
     infinity
    0.69
     fruition
    0.67
    eligible
    0.65
    clusions
    0.64
     remission
    0.64
    Activations Density 0.080%

    No Known Activations