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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & 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. 7-RES-JB
    6. 15749
    Prev
    Next
    INDEX
    Explanations

    mentions of the term 'gay'

    oai_token-act-pair · gpt-3.5-turbo

    references to gay individuals and issues related to the LGBTQ+ community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.70
    urers
    -0.70
     Manufacturer
    -0.70
    Condition
    -0.70
    PsyNetMessage
    -0.69
     sidx
    -0.68
     guiActiveUnfocused
    -0.68
    Dispatch
    -0.68
    Dur
    -0.67
    æ©Ł
    -0.67
    POSITIVE LOGITS
    atri
    0.94
     couples
    0.93
    dar
    0.91
    lord
    0.90
     marriage
    0.88
     slurs
    0.87
     bashing
    0.84
    ened
    0.81
     porn
    0.80
    ness
    0.80
    Activations Density 0.022%

    No Known Activations