© 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. 3-RES-JB
    11. 15545
    Prev
    Next
    INDEX
    Explanations

    references to the city "Rio" in the context of different topics such as sports, events, geography, and politics

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Rio," particularly in the context of events or locations associated with it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -+-+
    -0.68
     sqor
    -0.68
     sidel
    -0.67
     quirks
    -0.65
     HH
    -0.65
     McDonnell
    -0.64
     hover
    -0.64
    ibility
    -0.63
    ship
    -0.62
     deduction
    -0.62
    POSITIVE LOGITS
     Janeiro
    1.21
     Grande
    1.10
     Rio
    1.03
     Lumpur
    0.90
    rio
    0.90
    jas
    0.88
     Jiu
    0.87
    eco
    0.83
    zon
    0.82
    etta
    0.81
    Activations Density 0.009%

    No Known Activations