© 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 EvalsExportsinterp-engineNEWAPI 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. 11273
    Prev
    Next
    INDEX
    Explanations

    adjectives related to cuteness or attractiveness

    oai_token-act-pair · gpt-3.5-turbo

    descriptors related to cuteness and humor

    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
    uther
    -0.72
    ainer
    -0.72
    ership
    -0.72
    Ĥİ
    -0.70
    ieves
    -0.66
     Strongh
    -0.66
    ieved
    -0.66
    emale
    -0.66
    izen
    -0.65
    ĵ
    -0.64
    POSITIVE LOGITS
     little
    1.32
    glers
    1.05
    pants
    1.04
     stuff
    1.00
    ness
    0.97
     guy
    0.93
     sounding
    0.92
     shit
    0.92
    little
    0.91
     bastard
    0.90
    Activations Density 0.158%

    No Known Activations