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 49152
    5. 8-RES_FS49152-JB
    6. 26248
    Prev
    Next
    INDEX
    Explanations

    the word "Breaking" in various contexts related to news

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    113
    +0.10
    0.4%
    651
    +0.09
    0.4%
    550
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    113
    +0.10
    0.01
    606
    +0.09
    0.01
    651
    +0.09
    0.01
    Negative Logits
    inating
    -0.75
    yon
    -0.74
    rals
    -0.73
    minist
    -0.71
    wagen
    -0.70
    istry
    -0.69
    itance
    -0.68
    chev
    -0.68
    ican
    -0.66
    nery
    -0.66
    POSITIVE LOGITS
    fast
    1.13
     Bad
    0.87
     News
    0.78
     Breaking
    0.78
    views
    0.77
    down
    0.76
    through
    0.74
    AKING
    0.72
    Berry
    0.70
    edient
    0.70
    Activations Density 0.010%

    No Known Activations