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. 0-RES-JB
    6. 3644
    Prev
    Next
    INDEX
    Explanations

    phrases related to the LGBT community

    oai_token-act-pair · gpt-3.5-turbo

    mentions or discussions related to the LGBT community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     yield
    -0.71
    gran
    -0.69
     shells
    -0.66
     Maz
    -0.65
     shell
    -0.65
     scrape
    -0.65
    helm
    -0.64
     Simulator
    -0.63
    alin
    -0.63
     snapping
    -0.62
    POSITIVE LOGITS
     LGBT
    3.54
     LGBTQ
    2.86
    LGBT
    2.83
     gay
    2.29
     transgender
    2.13
     Transgender
    2.11
     gays
    2.05
     lesbian
    2.05
     Lesbian
    1.98
     homosexuals
    1.93
    Activations Density 0.021%

    No Known Activations