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. 6-RES-JB
    6. 8233
    Prev
    Next
    INDEX
    Explanations

    the words "ladies" and "gentlemen"

    oai_token-act-pair · gpt-3.5-turbo

    references to gender-specific terms, particularly 'ladies' and 'gentlemen'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ramid
    -0.74
    enf
    -0.72
    Fuel
    -0.72
    yrus
    -0.69
    aya
    -0.69
    erenn
    -0.67
    aeda
    -0.66
    Emb
    -0.65
    osta
    -0.64
    ilon
    -0.64
    POSITIVE LOGITS
     gentleman
    1.03
     gentlemen
    0.98
    entle
    0.76
     traveler
    0.73
     Gentleman
    0.72
    men
    0.72
    gery
    0.71
    owship
    0.70
    utenant
    0.68
    maid
    0.65
    Activations Density 0.030%

    No Known Activations