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. 19447
    Prev
    Next
    INDEX
    Explanations

    terms related to the LGBTQ+ community and issues around discrimination and support

    oai_token-act-pair · gpt-3.5-turbo

    references to the LGBTQ community and related topics

    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
    pmwiki
    -0.83
    ij士
    -0.78
    æ©Ł
    -0.73
     Closed
    -0.70
     weighted
    -0.68
     Wast
    -0.67
    nown
    -0.66
     ACTIONS
    -0.66
    Completed
    -0.64
    Contents
    -0.64
    POSITIVE LOGITS
    marriage
    0.82
     lesbian
    0.80
     Advocate
    0.74
     lesbians
    0.72
    roups
    0.70
    iyah
    0.68
    iland
    0.68
    doms
    0.67
    bia
    0.65
     empowerment
    0.65
    Activations Density 0.369%

    No Known Activations