© 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. 3-RES-JB
    11. 15799
    Prev
    Next
    INDEX
    Explanations

    words related to LGBTQ+ topics, particularly focusing on issues like homosexuality and discrimination

    oai_token-act-pair · gpt-3.5-turbo

    references to homosexuality and related issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãģį
    -0.70
     shroud
    -0.68
    UGE
    -0.68
     sender
    -0.64
    FORE
    -0.64
     dent
    -0.63
    BuyableInstoreAndOnline
    -0.62
    OUP
    -0.62
     indirect
    -0.60
    REE
    -0.60
    POSITIVE LOGITS
    emade
    1.37
    estead
    1.35
    ocaust
    1.06
    eless
    1.05
    osexual
    1.03
    neys
    1.01
    ework
    1.01
    icide
    0.96
    ogeneous
    0.96
    iny
    0.91
    Activations Density 0.003%

    No Known Activations