© 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. 12-RES-JB
    11. 3464
    Prev
    Next
    INDEX
    Explanations

    terms related to privacy violations, surveillance, and scandals involving high-profile individuals

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to political controversies and digital monitoring

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jews
    -1.21
    Jewish
    -1.21
    Jew
    -1.07
     Rabbi
    -1.03
     rabbi
    -1.00
    Han
    -0.99
     Jewish
    -0.97
    York
    -0.97
     Judaism
    -0.95
     Zion
    -0.95
    POSITIVE LOGITS
     Brazil
    2.14
     Brazilian
    2.13
    Brazil
    2.11
     Rousse
    2.05
     Sao
    1.97
     Bras
    1.82
     Rio
    1.78
     Paulo
    1.71
     Santos
    1.70
    ão
    1.69
    Activations Density 0.360%

    No Known Activations