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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 5-RES-JB
    6. 18678
    Prev
    Next
    INDEX
    Explanations

    names or terms related to the LGBTQ+ community, specifically focusing on the term "Gay."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Gay"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    5
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arily
    -0.78
    igslist
    -0.75
    yrim
    -0.75
    umbing
    -0.74
    uncture
    -0.69
     stockp
    -0.69
     payable
    -0.69
    IBLE
    -0.68
    ocobo
    -0.68
     conclud
    -0.67
    POSITIVE LOGITS
    nor
    1.07
    lord
    1.01
    bian
    0.98
    rier
    0.97
    lyn
    0.96
    dar
    0.91
    ther
    0.88
    lene
    0.86
     Marriage
    0.86
    zilla
    0.85
    Activations Density 0.012%

    No Known Activations