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. 23620
    Prev
    Next
    INDEX
    Explanations

    key phrases related to legal and official announcements

    oai_token-act-pair · gpt-4o-miniTriggered 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
    481
    +0.21
    1.0%
    447
    +0.15
    0.7%
    202
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    540
    +0.21
    0.06
    651
    +0.15
    0.06
    202
    +0.09
    0.05
    Negative Logits
    agog
    -0.67
    raviolet
    -0.63
    imble
    -0.59
    mbuds
    -0.59
    anium
    -0.57
     Operating
    -0.56
    Weather
    -0.56
    Live
    -0.55
    ombo
    -0.55
     Maintenance
    -0.54
    POSITIVE LOGITS
    fulness
    0.81
     itself
    0.76
     because
    0.73
     beforehand
    0.70
     happening
    0.69
     herself
    0.67
     anonymously
    0.65
    lessness
    0.65
     discrepancy
    0.65
    LINE
    0.64
    Activations Density 0.302%

    No Known Activations