© 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. 8-RES-JB
    11. 1173
    Prev
    Next
    INDEX
    Explanations

    phrases related to national identity and characteristics

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to national identity and cultural composition

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Remastered
    -0.86
    CD
    -0.67
    âĹ¼
    -0.63
    azines
    -0.62
     partName
    -0.62
    tz
    -0.62
    XM
    -0.62
     CJ
    -0.62
    bilt
    -0.61
    ptoms
    -0.61
    POSITIVE LOGITS
     sorts
    1.04
     choice
    0.89
     excellence
    0.84
     contrasts
    0.82
     fools
    0.77
     peace
    0.77
     utmost
    0.75
     thieves
    0.74
     convenience
    0.74
     moderation
    0.73
    Activations Density 0.173%

    No Known Activations