© 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. 3917
    Prev
    Next
    INDEX
    Explanations

    mathematical terms related to iterations and convergence in complex numbers

    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
    87
    +0.51
    2.9%
    459
    +0.18
    1.0%
    64
    +0.17
    0.9%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    87
    +0.51
    -0.01
    459
    +0.18
    0.08
    283
    +0.17
    0.02
    Negative Logits
     Pog
    -0.54
     Roose
    -0.49
     Coup
    -0.44
     spoiler
    -0.43
     Fake
    -0.41
     Canaver
    -0.41
    OIL
    -0.41
     Neb
    -0.41
     Notting
    -0.40
     Lydia
    -0.40
    POSITIVE LOGITS
     respectively
    1.08
    anwhile
    0.60
    collect
    0.58
     guiName
    0.58
    ]."
    0.56
    .).
    0.56
    *.
    0.55
    }.
    0.53
    ]).
    0.52
     collectively
    0.52
    Activations Density 2.372%

    No Known Activations