© 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 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. 9-RES-JB
    11. 20768
    Prev
    Next
    INDEX
    Explanations

    terms related to sexual activities involving the mouth

    oai_token-act-pair · gpt-3.5-turbo

    terms related to oral communication and sexual acts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alos
    -0.78
    rir
    -0.73
    uve
    -0.71
     Oops
    -0.70
    hov
    -0.69
    arent
    -0.69
     Scope
    -0.67
    tics
    -0.64
    alian
    -0.64
     Scand
    -0.64
    POSITIVE LOGITS
     submission
    0.99
     communication
    0.97
     transmission
    0.95
     submissions
    0.91
     presentations
    0.90
     presentation
    0.89
     communications
    0.89
     representations
    0.87
     transmissions
    0.85
     oral
    0.84
    Activations Density 0.083%

    No Known Activations