© 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. 1521
    Prev
    Next
    INDEX
    Explanations

    references to Hispanic and Latino populations

    oai_token-act-pair · gpt-3.5-turbo

    references to Hispanic or Latino identity and demographics

    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
    krit
    -0.84
    Ó
    -0.84
    erker
    -0.84
    aer
    -0.82
    ochond
    -0.80
    ĸļ
    -0.79
    ortmund
    -0.79
    uden
    -0.78
    essage
    -0.78
    soDeliveryDate
    -0.76
    POSITIVE LOGITS
     pes
    1.03
     immigrants
    0.94
     immigrant
    0.82
     Latinos
    0.79
     outreach
    0.76
     hots
    0.73
     youths
    0.73
     Latino
    0.73
     Nadu
    0.72
     immigration
    0.72
    Activations Density 0.021%

    No Known Activations