© 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. 9-RES-JB
    11. 21522
    Prev
    Next
    INDEX
    Explanations

    safety guidelines related to physical spaces

    oai_token-act-pair · gpt-3.5-turbo

    references to non-consensual acts and safety warnings regarding physical proximity and objects

    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
     renaissance
    -0.58
     Indie
    -0.57
    wow
    -0.57
     Merlin
    -0.56
     Strategy
    -0.55
     badass
    -0.54
     Prototype
    -0.53
     Startup
    -0.52
    found
    -0.52
     Blueprint
    -0.51
    POSITIVE LOGITS
     etc
    0.86
     unaccompanied
    0.79
     genitals
    0.77
     menstru
    0.74
     oneself
    0.72
     inappropriately
    0.72
     prohibited
    0.70
     preferring
    0.70
     spouses
    0.70
     adultery
    0.70
    Activations Density 0.822%

    No Known Activations