© 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. 0-RES-JB
    11. 2123
    Prev
    Next
    INDEX
    Explanations

    references to the country "Brazil"

    oai_token-act-pair · gpt-3.5-turbo

    references to Brazil

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     std
    -0.68
    oteric
    -0.66
    puter
    -0.65
    zie
    -0.65
     muzzle
    -0.65
    DH
    -0.64
    orah
    -0.63
     Zi
    -0.63
    pmwiki
    -0.63
    STD
    -0.62
    POSITIVE LOGITS
     Brazil
    3.56
    Brazil
    3.32
     Brazilian
    2.62
     Bolivia
    2.11
     Portugal
    2.09
     Argentina
    2.06
     Chile
    2.04
     Uruguay
    2.04
     Sao
    1.96
     Colombia
    1.96
    Activations Density 0.029%

    No Known Activations