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. 11-RES-JB
    6. 15585
    Prev
    Next
    INDEX
    Explanations

    content related to sexual acts and consent

    oai_token-act-pair · gpt-3.5-turbo

    sexually explicit content and terminology related to sexual acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Barkley
    -0.81
    veland
    -0.80
    stack
    -0.77
    Bah
    -0.76
     Towns
    -0.76
    bish
    -0.75
     Greenpeace
    -0.75
    Rogue
    -0.73
    quote
    -0.73
     unemploy
    -0.72
    POSITIVE LOGITS
     orgasm
    2.03
     ejac
    2.02
     clitor
    1.98
     vaginal
    1.71
     masturbation
    1.58
     semen
    1.58
     arousal
    1.58
     lubric
    1.54
     intercourse
    1.51
     erotic
    1.49
    Activations Density 0.490%

    No Known Activations