© 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 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. 6-RES-JB
    11. 18056
    Prev
    Next
    INDEX
    Explanations

    references to the city "Rio de Janeiro."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Rio de Janeiro in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rity
    -0.70
    -+-+
    -0.70
    iaries
    -0.69
     deviation
    -0.66
     comprom
    -0.66
    */(
    -0.65
    QB
    -0.64
     wills
    -0.64
    uyomi
    -0.64
    heartedly
    -0.64
    POSITIVE LOGITS
     Janeiro
    1.18
     Grande
    1.13
    zon
    0.91
    borg
    0.90
    rio
    0.88
     Ferdinand
    0.86
    etta
    0.86
     Jiu
    0.84
     Rio
    0.82
    jas
    0.81
    Activations Density 0.014%

    No Known Activations