© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 21806
    Prev
    Next
    INDEX
    Explanations

    mentions of Chinese nationality or culture

    oai_token-act-pair · gpt-3.5-turbo

    references to Chinese and Asian identities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    utherford
    -0.91
    esville
    -0.88
    lier
    -0.84
    odder
    -0.82
    tyard
    -0.81
    track
    -0.81
    ively
    -0.80
    lessly
    -0.78
     Barrett
    -0.78
    gart
    -0.77
    POSITIVE LOGITS
     immigrants
    0.87
     lantern
    0.87
     immigrant
    0.84
     ancestry
    0.82
     invaders
    0.81
     nationals
    0.81
     Nadu
    0.78
     takeaway
    0.77
     learners
    0.76
     descent
    0.76
    Activations Density 0.085%

    No Known Activations