© 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. 5093
    Prev
    Next
    INDEX
    Explanations

    phrases related to global issues and crises

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

    terms related to crises and critical situations in various contexts

    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
    posts
    -0.87
    parts
    -0.79
    tips
    -0.77
     positions
    -0.76
     Members
    -0.75
     Components
    -0.74
     Locations
    -0.74
    groups
    -0.74
     Publications
    -0.74
     directions
    -0.74
    POSITIVE LOGITS
     epidemic
    1.52
     crisis
    1.43
     tsunami
    1.41
     apocalypse
    1.40
    risis
    1.31
     renaissance
    1.26
     famine
    1.26
    ocalypse
    1.25
     blackout
    1.25
     slump
    1.23
    Activations Density 0.635%

    No Known Activations