© 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. 10-RES-JB
    11. 11143
    Prev
    Next
    INDEX
    Explanations

    explicit references to male and female genitalia

    oai_token-act-pair · gpt-3.5-turbo

    terms related to male and female genitalia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    quickShipAvailable
    -1.01
     Flavoring
    -0.78
     GOODMAN
    -0.74
     lawy
    -0.74
     partName
    -0.71
    uci
    -0.68
    IPS
    -0.67
    rish
    -0.65
    ravel
    -0.65
    HCR
    -0.63
    POSITIVE LOGITS
     ejac
    1.15
     enlarg
    1.00
     penis
    0.95
     genital
    0.90
     glands
    0.89
     foreskin
    0.88
     shaft
    0.87
     stimulating
    0.86
     masturb
    0.86
     canal
    0.85
    Activations Density 0.070%

    No Known Activations