© 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. 3769
    Prev
    Next
    INDEX
    Explanations

    information related to the ornithological topic of birds, particularly discussing various species and their characteristics

    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
    496
    +0.11
    0.5%
    223
    +0.11
    0.5%
    610
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    126
    +0.11
    0.03
    223
    +0.11
    0.04
    647
    +0.10
    0.03
    Negative Logits
     distractions
    -0.79
     frustrations
    -0.79
     rentals
    -0.78
     Vanity
    -0.78
     distraction
    -0.78
     lockout
    -0.76
    Deal
    -0.75
     frustration
    -0.75
    quickShipAvailable
    -0.74
    Kick
    -0.74
    POSITIVE LOGITS
     genus
    1.65
     extinct
    1.56
    aceae
    1.49
     species
    1.40
     phylogen
    1.31
     Species
    1.28
     mammalian
    1.26
    idae
    1.24
     hapl
    1.23
    ensis
    1.23
    Activations Density 0.468%

    No Known Activations