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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 2821
    Prev
    Next
    INDEX
    Explanations

    descriptions or accounts of sexual encounters

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual acts and allegations surrounding them

    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
     Architects
    -0.78
     pessim
    -0.76
     XCOM
    -0.75
     prag
    -0.73
     certs
    -0.72
    veland
    -0.72
    ItemTracker
    -0.71
     Startup
    -0.70
     Merchants
    -0.69
    é¾
    -0.69
    POSITIVE LOGITS
     sexually
    1.71
     sexual
    1.70
    Sexual
    1.60
     lewd
    1.60
     sex
    1.54
     masturbation
    1.52
     intercourse
    1.51
     vaginal
    1.47
     kissing
    1.47
     masturb
    1.46
    Activations Density 0.578%

    No Known Activations