© 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. 4-RES-JB
    11. 12482
    Prev
    Next
    INDEX
    Explanations

    terms related to the Rohingya Muslim crisis in Myanmar

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rohingya crisis and the country of Myanmar

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

    No Comments

    Negative Logits
    age
    -0.85
     posit
    -0.73
     Spielberg
    -0.73
     Geh
    -0.72
     Cobb
    -0.72
    Catal
    -0.72
    heet
    -0.68
     Mayer
    -0.68
     snipp
    -0.67
    busters
    -0.67
    POSITIVE LOGITS
     Myanmar
    1.08
    anmar
    1.01
    aution
    0.88
     Rohing
    0.76
     Burma
    0.76
     Buddhist
    0.76
     Uz
    0.75
     Pradesh
    0.75
     Shan
    0.73
     Bangl
    0.73
    Activations Density 0.013%

    No Known Activations