© 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. 3901
    Prev
    Next
    INDEX
    Explanations

    references to a specific country and its crisis involving the Rohingya Muslims

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Rohingya and Myanmar, particularly in relation to the crisis affecting that population

    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
    age
    -0.91
    rier
    -0.85
     Geh
    -0.82
    ivity
    -0.74
     Cobb
    -0.73
     iP
    -0.73
    matic
    -0.73
    Catal
    -0.71
    RH
    -0.71
    heet
    -0.71
    POSITIVE LOGITS
     Myanmar
    1.35
    anmar
    1.16
     Rohing
    1.06
     Rohingya
    0.97
    aution
    0.90
     tradem
    0.90
     Buddhist
    0.90
     Bangl
    0.87
     Burma
    0.83
    arthed
    0.83
    Activations Density 0.012%

    No Known Activations