© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Feature Splitting for GPT2-Small
    5. GPT2-Small
    7. Residual Feature Splitting 24576
    9. 8-RES_FS24576-JB
    11. 15563
    Prev
    Next
    INDEX
    Explanations

    the location "Osorio Chong" in news articles

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    659
    +0.12
    0.6%
    549
    +0.11
    0.5%
    345
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.12
    0.02
    345
    +0.11
    0.01
    511
    +0.11
    0.01
    Negative Logits
    rence
    -0.72
    ered
    -0.67
    llah
    -0.65
    ingly
    -0.64
    ILLE
    -0.63
     grounds
    -0.61
    tenance
    -0.61
    ãĥ¼ãĥĨãĤ£
    -0.60
    EEE
    -0.59
    Footnote
    -0.57
    POSITIVE LOGITS
    pite
    1.01
    awa
    0.99
    ensible
    0.96
    ullivan
    0.95
    atell
    0.94
    ensibly
    0.93
    por
    0.92
    hiba
    0.92
    oma
    0.91
    orrow
    0.91
    Activations Density 0.016%

    No Known Activations