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

    Neuronpedia

    Jacobian LensNEW
    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. 21851
    Prev
    Next
    INDEX
    Explanations

    the word "dude" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to male individuals, particularly using the term "dude."

    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
    pring
    -0.85
    oor
    -0.72
    andowski
    -0.71
    ":["
    -0.71
    ood
    -0.71
    atories
    -0.71
    Union
    -0.70
    inters
    -0.68
    iegel
    -0.67
    ulton
    -0.66
    POSITIVE LOGITS
     dude
    1.07
     dudes
    0.90
    holes
    0.87
     Dude
    0.81
    hole
    0.80
     Valiant
    0.73
     asshole
    0.71
     Damn
    0.71
    swer
    0.69
     pics
    0.69
    Activations Density 0.011%

    No Known Activations