© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 12520
    Prev
    Next
    INDEX
    Explanations

    terms related to the Rohingya Muslim community in Myanmar and their plight, including mentions of oppression, displacement, fleeing, and international responses

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rohingya Muslim community and their plight

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.80
    ifice
    -0.75
     ellipt
    -0.74
     malf
    -0.72
     exec
    -0.72
    neau
    -0.72
     Investigator
    -0.70
     reviewer
    -0.67
     Majesty
    -0.67
    Bloomberg
    -0.66
    POSITIVE LOGITS
     militias
    0.93
     villages
    0.93
     indigenous
    0.93
     tribal
    0.91
     protesting
    0.90
     revolt
    0.90
     militia
    0.89
     migrated
    0.87
     tribes
    0.87
     separatists
    0.87
    Activations Density 0.548%

    No Known Activations