© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 15829
    Prev
    Next
    INDEX
    Explanations

    references or mentions of the LGBTQ+ community

    oai_token-act-pair · gpt-3.5-turbo

    references to the LGBTQ+ community and related issues

    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
     origin
    -0.75
     maintenance
    -0.73
     plates
    -0.73
     Ed
    -0.72
     Stan
    -0.71
     station
    -0.69
     dull
    -0.69
     medium
    -0.68
     thought
    -0.68
     Field
    -0.68
    POSITIVE LOGITS
    LGBT
    3.50
    Jews
    1.22
    abortion
    1.16
    VPN
    1.15
    Muslim
    1.15
    Bey
    1.14
    Pope
    1.13
    gay
    1.13
    soType
    1.12
    Sexual
    1.11
    Activations Density 0.035%

    No Known Activations