© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 2330
    Prev
    Next
    INDEX
    Explanations

    phrases related to political sanctions and international relations, specifically regarding Russia and the Kremlin

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to diplomatic tensions and military conflicts involving Russia

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    Oracle
    -0.84
    eteria
    -0.75
    ascript
    -0.74
    aez
    -0.72
    CLA
    -0.72
    ARI
    -0.71
    Ju
    -0.69
    estro
    -0.67
    Surv
    -0.67
    aqu
    -0.67
    POSITIVE LOGITS
     Crimea
    1.65
     Ukraine
    1.55
     Belarus
    1.38
     Kiev
    1.37
     Crimean
    1.36
     Putin
    1.35
     annexation
    1.35
     Ukrainians
    1.35
     Baltic
    1.35
     Ukrainian
    1.32
    Activations Density 0.298%

    No Known Activations