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. 13822
    Prev
    Next
    INDEX
    Explanations

    references to females, specifically using the word "girl"

    oai_token-act-pair · gpt-3.5-turbo

    references to "girl" in various 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
    insula
    -0.91
    aeda
    -0.89
     contiguous
    -0.78
    raltar
    -0.77
    psey
    -0.74
    aution
    -0.74
    PDATE
    -0.73
    erenn
    -0.73
    etsk
    -0.72
    rawdownloadcloneembedreportprint
    -0.71
    POSITIVE LOGITS
     Scouts
    1.02
    hood
    0.98
    ishly
    0.96
    girl
    0.86
    ish
    0.86
     girls
    0.84
    girls
    0.81
     girl
    0.80
    glers
    0.79
    bag
    0.79
    Activations Density 0.017%

    No Known Activations