© 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. 0-RES-JB
    11. 16390
    Prev
    Next
    INDEX
    Explanations

    names or terms related to people of Asian descent

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Berks
    -0.97
    Harris
    -0.86
     meteor
    -0.83
    Mars
    -0.74
     Schr
    -0.74
    Philadelphia
    -0.73
    rolet
    -0.70
    Sch
    -0.70
    Ram
    -0.69
     comet
    -0.66
    POSITIVE LOGITS
     Tong
    4.04
     tong
    1.66
     Wong
    1.48
     Fiji
    1.41
     tongues
    1.32
     Samoa
    1.30
     Yong
    1.25
     Brune
    1.11
     Gou
    1.09
     Mold
    1.08
    Activations Density 0.053%

    No Known Activations