© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 20873
    Prev
    Next
    INDEX
    Explanations

    references to the country "Brazil" and related events or entities

    oai_token-act-pair · gpt-3.5-turbo

    references to Brazil and related cultural aspects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WARE
    -0.73
    ################
    -0.70
    boarding
    -0.70
    OSP
    -0.69
    ################################
    -0.66
     Mercer
    -0.66
    ellen
    -0.64
    ancies
    -0.64
    creen
    -0.63
    sworth
    -0.62
    POSITIVE LOGITS
     Jiu
    1.28
     Paulo
    1.10
    ians
    1.05
     Portuguese
    1.03
    ão
    1.01
    inho
    0.92
     Janeiro
    0.90
    ienne
    0.87
     Brazilian
    0.86
    ian
    0.86
    Activations Density 0.052%

    No Known Activations