© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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 49152
    9. 8-RES_FS49152-JB
    11. 45550
    Prev
    Next
    INDEX
    Explanations

    narratives involving parent-child relationships, particularly focusing on fathers and their children

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_fs49152-jb
    Configuration
    jbloom/GPT2-Small-Feature-Splitting-Experiment-Layer-8/blocks.8.hook_resid_pre_49152
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    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
    278
    +0.11
    0.5%
    556
    +0.10
    0.5%
    38
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    278
    +0.11
    0.02
    639
    +0.10
    0.02
    318
    +0.10
    0.02
    Negative Logits
    ioxide
    -0.88
    otos
    -0.78
    IUM
    -0.78
    BTC
    -0.77
    nit
    -0.76
    Quant
    -0.71
     Flavoring
    -0.69
    ilib
    -0.68
    risome
    -0.68
    Ĥª
    -0.67
    POSITIVE LOGITS
     grandparents
    1.32
     grandmother
    1.24
     daughters
    1.15
     daughter
    1.09
     grandfather
    1.09
     sisters
    1.03
     sons
    1.03
     husbands
    1.03
     siblings
    1.02
    daughter
    1.01
    Activations Density 0.082%

    No Known Activations