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. 11-RES-JB
    6. 8063
    Prev
    Next
    INDEX
    Explanations

    the title "Ms" with a range of numbers following it

    oai_token-act-pair · gpt-3.5-turbo

    references to women, specifically those addressed as "Ms." in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     destro
    -0.80
     compr
    -0.73
    ornia
    -0.73
    »Ĵ
    -0.70
     techno
    -0.66
    SIGN
    -0.65
    obar
    -0.64
     industrial
    -0.63
     nightly
    -0.63
    ype
    -0.62
    POSITIVE LOGITS
     Sturgeon
    1.16
     Merkel
    0.94
     Marie
    0.94
     Fiorina
    0.88
     Grace
    0.88
     Pelosi
    0.88
     Rowling
    0.88
     Elizabeth
    0.86
     Anne
    0.84
     Abedin
    0.83
    Activations Density 0.019%

    No Known Activations