© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1905
    Prev
    Next
    INDEX
    Explanations

    references to the violent crisis involving Rohingya Muslims in Myanmar

    oai_token-act-pair · gpt-3.5-turbo

    references to the Rohingya and Myanmar

    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
    age
    -0.87
    rier
    -0.76
    Catal
    -0.73
    clip
    -0.73
     posit
    -0.72
    abet
    -0.69
    ces
    -0.69
    hips
    -0.68
    aday
    -0.68
    rium
    -0.68
    POSITIVE LOGITS
     Myanmar
    1.20
    anmar
    1.01
     Pradesh
    0.93
    aution
    0.92
     Rohing
    0.84
     Burma
    0.79
     Rohingya
    0.77
     Buddhist
    0.77
     Bangladesh
    0.77
     Laos
    0.76
    Activations Density 0.009%

    No Known Activations