© 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
    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. 20486
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual content and adult industry

    oai_token-act-pair · gpt-3.5-turbo

    references to pornography and sexual themes

    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
     Blizz
    -0.99
    stack
    -0.95
    externalActionCode
    -0.88
     WTO
    -0.87
    rolet
    -0.87
     Chero
    -0.86
    grain
    -0.84
     Tata
    -0.82
     Farming
    -0.82
     Atkinson
    -0.79
    POSITIVE LOGITS
     masturbation
    2.16
     porn
    2.16
     masturb
    2.12
     erotic
    2.11
     pornography
    2.07
     Porn
    2.06
     pornographic
    2.05
     sex
    1.94
     ejac
    1.91
     sexual
    1.90
    Activations Density 0.532%

    No Known Activations