Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 10907
    Prev
    Next
    INDEX
    Explanations

    the word "bro" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    the slang term "bro" used frequently in casual or conversational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URA
    -0.77
    ++++++++++++++++
    -0.70
    ãĥĨãĤ£
    -0.69
    ENC
    -0.69
    EPA
    -0.69
    ãĤ¦ãĤ¹
    -0.68
    Catal
    -0.67
    URI
    -0.67
    ById
    -0.65
    ARB
    -0.65
    POSITIVE LOGITS
    swer
    0.98
     bro
    0.89
    chet
    0.89
    oks
    0.88
    thel
    0.87
    idered
    0.86
    cade
    0.86
    etooth
    0.85
    dy
    0.85
    gue
    0.82
    Activations Density 0.007%

    No Known Activations