© 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. 7-RES-JB
    11. 12428
    Prev
    Next
    INDEX
    Explanations

    references to the city "Rio" and events or activities related to Rio de Janeiro, potentially in a news or sports context

    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 @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rity
    -0.70
    iaries
    -0.67
     comprom
    -0.67
    espie
    -0.66
     clipboard
    -0.66
    -+-+
    -0.66
     deviation
    -0.63
     McDonnell
    -0.63
    ocene
    -0.63
    arily
    -0.62
    POSITIVE LOGITS
     Janeiro
    1.23
     Grande
    1.14
    rio
    0.97
     Ferdinand
    0.95
     Jiu
    0.94
    etta
    0.93
    zon
    0.92
    jas
    0.91
     Olympics
    0.85
     Rio
    0.84
    Activations Density 0.019%

    No Known Activations