© 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 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. 10-RES-JB
    11. 5869
    Prev
    Next
    INDEX
    Explanations

    references to societal or political unrest in different regions

    oai_token-act-pair · gpt-3.5-turbo

    references to specific locations or events occurring in various places

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leans
    -0.80
    lot
    -0.78
    natureconservancy
    -0.72
    omething
    -0.70
    oola
    -0.69
    NESS
    -0.68
    pointers
    -0.68
    é¾įå¥ij士
    -0.67
    minist
    -0.67
    sers
    -0.66
    POSITIVE LOGITS
     Ukraine
    1.33
     Catalonia
    1.29
     Syria
    1.28
     Libya
    1.25
     Charlottesville
    1.20
     Venezuela
    1.20
     Yemen
    1.19
     Crimea
    1.19
     Gaza
    1.19
     Ferguson
    1.16
    Activations Density 0.189%

    No Known Activations