© 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
    2. Joseph Bloom · Feature Splitting for GPT2-Small
    3. GPT2-Small
    4. Residual Feature Splitting 24576
    5. 8-RES_FS24576-JB
    6. 24196
    Prev
    Next
    INDEX
    Explanations

    references to parenthood and parental roles

    oai_token-act-pair · gpt-4o-miniTriggered 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
    343
    +0.10
    0.5%
    372
    +0.10
    0.5%
    459
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    343
    +0.10
    0.02
    711
    +0.10
    0.01
    758
    +0.10
    0.01
    Negative Logits
    anwhile
    -0.77
     Antar
    -0.75
     Limbaugh
    -0.69
    jriwal
    -0.67
    paio
    -0.63
    atility
    -0.62
     Granger
    -0.61
    punk
    -0.59
    oppy
    -0.58
     marrow
    -0.58
    POSITIVE LOGITS
    hetical
    1.61
    hesis
    1.55
    heses
    1.42
    hetically
    1.28
    hes
    0.92
    hood
    0.91
    age
    0.86
    ament
    0.78
    parents
    0.76
    Node
    0.76
    Activations Density 0.023%

    No Known Activations