© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 22555
    Prev
    Next
    INDEX
    Explanations

    C++ programming constructs, particularly focusing on syntax related to inclusion and template declarations

    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
    373
    +0.13
    0.6%
    730
    +0.12
    0.5%
    609
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    160
    +0.13
    0.03
    158
    +0.12
    0.02
    699
    +0.10
    0.02
    Negative Logits
     Osiris
    -0.82
    halla
    -0.82
     oranges
    -0.81
    vana
    -0.71
    76561
    -0.71
    votes
    -0.70
     Rewards
    -0.67
    Mars
    -0.67
     karma
    -0.66
    pring
    -0.66
    POSITIVE LOGITS
     std
    1.16
    std
    0.97
    ++
    0.93
     printf
    0.88
    ++)
    0.87
     Vec
    0.83
    printf
    0.82
     sizeof
    0.82
     cout
    0.78
     unsigned
    0.76
    Activations Density 0.053%

    No Known Activations