© 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. 1-RES-JB
    11. 3522
    Prev
    Next
    INDEX
    Explanations

    phrases related to global organizations or events

    oai_token-act-pair · gpt-3.5-turbo

    the term "World" in various contexts, often related to significant global events or organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     actionGroup
    -0.94
    EStream
    -0.92
    veyard
    -0.88
    interstitial
    -0.80
    merce
    -0.79
    MENTS
    -0.79
    ibilities
    -0.78
    Downloadha
    -0.78
    etsk
    -0.78
    olulu
    -0.75
    POSITIVE LOGITS
     Reincarn
    0.89
     World
    0.87
     Championships
    0.83
     Cup
    0.82
     Series
    0.80
     Heritage
    0.80
     Confederation
    0.79
     Order
    0.79
     League
    0.78
    World
    0.77
    Activations Density 0.022%

    No Known Activations