© 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 EvalsExportsAPI 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. 10416
    Prev
    Next
    INDEX
    Explanations

    terms related to the biology and anatomy of vertebrates, especially mammals

    oai_token-act-pair · gpt-3.5-turboTriggered 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
    575
    +0.16
    0.7%
    151
    +0.14
    0.6%
    227
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    575
    +0.16
    0.03
    151
    +0.14
    0.03
    288
    +0.11
    0.02
    Negative Logits
    field
    -0.70
    inventoryQuantity
    -0.70
    mire
    -0.69
    quote
    -0.67
    zona
    -0.67
    iffe
    -0.66
    FIN
    -0.64
    bomb
    -0.63
     Proposition
    -0.63
    fill
    -0.62
    POSITIVE LOGITS
     carniv
    1.25
     mammals
    1.23
    brates
    1.16
     species
    1.15
     mammal
    1.13
     biologists
    1.06
     mammalian
    1.06
     fossils
    1.04
     primates
    1.03
     genus
    1.00
    Activations Density 0.046%

    No Known Activations