© 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. 3-RES-JB
    11. 16965
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, specifically Peru and Bolivia

    oai_token-act-pair · gpt-3.5-turbo

    mentions of South American countries, particularly Peru and Bolivia

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.95
    ////////////////
    -0.86
    hips
    -0.81
    ////////////////////////////////
    -0.77
    services
    -0.76
    ulation
    -0.76
    sg
    -0.75
    haw
    -0.74
    busters
    -0.72
    alions
    -0.70
    POSITIVE LOGITS
     Peru
    0.95
    uvian
    0.79
     Rican
    0.76
     Bolivia
    0.76
    illo
    0.71
     Pradesh
    0.69
     Jiu
    0.67
    asonic
    0.66
     earthquake
    0.66
     Vie
    0.66
    Activations Density 0.008%

    No Known Activations