© 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. 0-RES-JB
    11. 13753
    Prev
    Next
    INDEX
    Explanations

    the colloquial term "bro" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "bro."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uple
    -0.78
     UL
    -0.70
    ALS
    -0.69
    lement
    -0.68
     Personality
    -0.67
     Scion
    -0.66
     \(
    -0.65
    Application
    -0.64
     \(\
    -0.64
    raction
    -0.63
    POSITIVE LOGITS
     bro
    3.97
    bro
    1.65
    Bro
    1.61
     Bro
    1.54
     prostitution
    1.23
     prostitutes
    1.12
     bud
    1.11
     whore
    1.07
     john
    1.05
     Bros
    1.05
    Activations Density 0.017%

    No Known Activations