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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 10194
    Prev
    Next
    INDEX
    Explanations

    words related to sexual activities

    oai_token-act-pair · gpt-3.5-turbo

    references to sexual activity, particularly involving specific relationships or circumstances

    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
     lawy
    -0.75
     millenn
    -0.67
    Label
    -0.67
    amin
    -0.62
     rubble
    -0.62
    Reviewer
    -0.61
    eli
    -0.61
     toughness
    -0.61
    Americ
    -0.60
     resilience
    -0.59
    POSITIVE LOGITS
     intercourse
    1.11
     orgasm
    1.03
     with
    0.96
     WITH
    0.91
     consensual
    0.91
     adultery
    0.89
    omnia
    0.89
    essions
    0.88
     fantasies
    0.87
    irgin
    0.85
    Activations Density 0.071%

    No Known Activations