© 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. 26835
    Prev
    Next
    INDEX
    Explanations

    phrases that imply guidance or advice

    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
    373
    +0.11
    0.5%
    377
    +0.10
    0.4%
    672
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    566
    +0.11
    0.05
    212
    +0.10
    0.04
    763
    +0.09
    0.04
    Negative Logits
    etics
    -0.67
     gui
    -0.64
    catentry
    -0.63
    Struct
    -0.63
    Parameters
    -0.62
     stabilization
    -0.60
    andowski
    -0.59
     Direction
    -0.59
     phys
    -0.59
    GUI
    -0.59
    POSITIVE LOGITS
     yourselves
    1.15
     yourself
    0.98
     reading
    0.86
     listening
    0.82
     watching
    0.78
     wondering
    0.77
     Yourself
    0.73
    tainment
    0.72
     YOUR
    0.72
     spoilers
    0.71
    Activations Density 0.223%

    No Known Activations