© 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. 14957
    Prev
    Next
    INDEX
    Explanations

    phrases related to discussions or opinions being expressed

    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
    19
    +0.10
    0.4%
    430
    +0.10
    0.4%
    247
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.10
    0.09
    274
    +0.10
    0.07
    540
    +0.09
    0.08
    Negative Logits
    ETHOD
    -0.65
     inver
    -0.64
    oiler
    -0.63
    tics
    -0.63
    MpServer
    -0.62
     unpop
    -0.61
    artifacts
    -0.61
    vernight
    -0.61
    waters
    -0.61
     tert
    -0.59
    POSITIVE LOGITS
     bestowed
    1.07
     emanating
    0.92
     exchanged
    0.90
     undertaken
    0.90
     levied
    0.90
     handed
    0.88
     uttered
    0.86
     issued
    0.85
     afforded
    0.81
     received
    0.80
    Activations Density 0.717%

    No Known Activations