© 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. 15561
    Prev
    Next
    INDEX
    Explanations

    expressions related to opinions or beliefs

    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
    581
    +0.13
    0.6%
    749
    +0.10
    0.5%
    463
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    463
    +0.13
    0.03
    299
    +0.10
    0.03
    363
    +0.10
    0.02
    Negative Logits
    urrection
    -0.67
     anonymity
    -0.64
    urers
    -0.64
     Recovery
    -0.63
    anmar
    -0.62
    undo
    -0.59
     ultras
    -0.57
    ilies
    -0.55
     Medals
    -0.55
    interstitial
    -0.55
    POSITIVE LOGITS
    pires
    1.12
    soever
    0.98
     imaginable
    0.92
     knows
    0.88
     subscrib
    0.87
     ever
    0.81
     whatsoever
    0.81
     slightest
    0.80
     EVER
    0.78
     remotely
    0.77
    Activations Density 0.121%

    No Known Activations