© 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. 2-RES-JB
    11. 17473
    Prev
    Next
    INDEX
    Explanations

    mentions of the LGBT community

    oai_token-act-pair · gpt-3.5-turbo

    references to homosexuality and related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.78
     shroud
    -0.68
    UGE
    -0.65
    BuyableInstoreAndOnline
    -0.65
     Krug
    -0.65
     Delta
    -0.62
     dent
    -0.62
    REE
    -0.62
    FUL
    -0.61
    EMENT
    -0.61
    POSITIVE LOGITS
    emade
    1.34
    estead
    1.34
    neys
    1.06
    ocaust
    1.04
    onym
    1.01
    ogeneous
    1.01
    eless
    1.00
    osexual
    1.00
    ework
    0.99
    icide
    0.98
    Activations Density 0.003%

    No Known Activations