© 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. 14949
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format

    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
    296
    +0.14
    0.7%
    606
    +0.13
    0.6%
    12
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.14
    0.05
    606
    +0.13
    0.04
    659
    +0.12
    0.04
    Negative Logits
     Carbuncle
    -0.82
     Laur
    -0.80
    éļ
    -0.78
     AF
    -0.76
     Hawai
    -0.76
     Hunters
    -0.74
    Controller
    -0.74
     Ao
    -0.74
     Giov
    -0.73
    aido
    -0.72
    POSITIVE LOGITS
    ter
    1.12
    ters
    1.08
    tering
    1.07
    TER
    1.05
    tera
    0.95
    tered
    0.92
    cember
    0.89
    ental
    0.87
    down
    0.85
    enting
    0.85
    Activations Density 0.177%

    No Known Activations