© 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. 20565
    Prev
    Next
    INDEX
    Explanations

    phrases related to sexual activities and relationships

    oai_token-act-pair · gpt-3.5-turbo

    terms related to sexual activity and relationships

    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
     lawy
    -0.77
    eco
    -0.73
     dilig
    -0.71
    Reviewer
    -0.70
     resilience
    -0.70
     millenn
    -0.70
    quickShipAvailable
    -0.67
    Americ
    -0.66
     recycling
    -0.62
     Gerr
    -0.62
    POSITIVE LOGITS
     intercourse
    1.08
     orgasm
    1.03
     adultery
    0.95
    Sexual
    0.90
    irgin
    0.87
     consensual
    0.86
     with
    0.86
     WITH
    0.86
     fantasies
    0.82
     climax
    0.80
    Activations Density 0.101%

    No Known Activations