© 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. 45761
    Prev
    Next
    INDEX
    Explanations

    references to pain or painful experiences

    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
    151
    +0.14
    0.7%
    288
    +0.12
    0.6%
    730
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    151
    +0.14
    0.02
    730
    +0.12
    0.01
    669
    +0.11
    0.01
    Negative Logits
    ership
    -1.01
    uve
    -0.97
    izen
    -0.90
    yip
    -0.83
    available
    -0.82
    annis
    -0.80
    agall
    -0.79
    adem
    -0.77
    swick
    -0.77
    fund
    -0.76
    POSITIVE LOGITS
     reminders
    1.09
     painful
    1.02
     reminder
    0.99
     memories
    0.95
     pain
    0.95
     childbirth
    0.91
     scars
    0.84
     trauma
    0.83
     feelings
    0.82
     discomfort
    0.82
    Activations Density 0.017%

    No Known Activations