© 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. 9-RES-JB
    11. 4210
    Prev
    Next
    INDEX
    Explanations

    mentions of countries, specifically focusing on Iceland

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <<
    -0.70
    LESS
    -0.70
    avez
    -0.69
     DOE
    -0.65
    agonist
    -0.63
    ++++
    -0.61
    anu
    -0.61
    adobe
    -0.61
     Yelp
    -0.61
     DeVos
    -0.60
    POSITIVE LOGITS
    sson
    1.11
     Ragnar
    1.04
     Viking
    0.99
     Icelandic
    0.98
    kj
    0.94
    lund
    0.92
    ð
    0.89
    ersen
    0.84
     Andersen
    0.83
    borg
    0.83
    Activations Density 0.080%

    No Known Activations