© 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 · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 1-RES-JB
    11. 3783
    Prev
    Next
    INDEX
    Explanations

    the word or variations of "impulse."

    oai_token-act-pair · gpt-3.5-turbo

    references to human desires and impulses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    said
    -0.76
    wordpress
    -0.75
    mberg
    -0.70
    rooms
    -0.70
    gaard
    -0.70
    aning
    -0.69
    orkshire
    -0.69
    ndum
    -0.68
    ondo
    -0.68
    oln
    -0.68
    POSITIVE LOGITS
     impulse
    1.45
     impulses
    1.00
     instinct
    0.94
     gratification
    0.90
     urge
    0.82
    ulse
    0.81
    oleon
    0.80
     reper
    0.79
     instinctively
    0.78
    wcs
    0.77
    Activations Density 0.005%

    No Known Activations