© 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. 2-RES-JB
    11. 11764
    Prev
    Next
    INDEX
    Explanations

    keywords related to the city "Rio"

    oai_token-act-pair · gpt-3.5-turbo

    references to the city of Rio de Janeiro

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -+-+
    -0.67
    edly
    -0.66
     wills
    -0.65
     CPC
    -0.64
    ATURE
    -0.63
     McDonnell
    -0.63
     HH
    -0.63
    ibility
    -0.63
     quirks
    -0.63
    ancies
    -0.62
    POSITIVE LOGITS
     Janeiro
    1.18
     Grande
    1.15
     Rio
    1.07
     Jiu
    0.91
    rio
    0.90
    jas
    0.88
    Äį
    0.83
     Paulo
    0.82
    zon
    0.82
     Lumpur
    0.81
    Activations Density 0.005%

    No Known Activations