© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14110
    Prev
    Next
    INDEX
    Explanations

    mentions of different countries and regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of countries and regions

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ioned
    -0.70
    rious
    -0.69
    henko
    -0.68
     deposition
    -0.61
     confirmation
    -0.61
    hement
    -0.59
    msg
    -0.57
    cript
    -0.56
    veyard
    -0.54
    naissance
    -0.53
    POSITIVE LOGITS
     economically
    0.74
    wide
    0.71
     economy
    0.66
    ians
    0.66
     City
    0.66
     populace
    0.64
    's
    0.64
     electorate
    0.63
     GDP
    0.63
     taxpayers
    0.62
    Activations Density 0.367%

    No Known Activations