© 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. 2-RES-JB
    11. 19741
    Prev
    Next
    INDEX
    Explanations

    locations and events in war zones

    oai_token-act-pair · gpt-3.5-turbo

    terms related to geographic locations and significant events occurring in those areas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cary
    -0.76
     Wonderland
    -0.75
    Scot
    -0.75
     Lifetime
    -0.73
     Packers
    -0.69
     Cobb
    -0.67
     Hitchcock
    -0.67
    Seattle
    -0.66
    Wisconsin
    -0.66
     Hubbard
    -0.66
    POSITIVE LOGITS
     Rohingya
    0.99
     Daesh
    0.93
     Islamist
    0.92
     jihadist
    0.90
     Azerbai
    0.90
     shelling
    0.89
     militants
    0.88
     Ankara
    0.88
     Jinping
    0.87
     detained
    0.87
    Activations Density 2.141%

    No Known Activations