© 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. 6-RES-JB
    11. 14821
    Prev
    Next
    INDEX
    Explanations

    references to Armenian-related terms or topics

    oai_token-act-pair · gpt-3.5-turbo

    references to Armenian history, culture, and related geopolitical topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ership
    -0.99
    ularity
    -0.96
    ered
    -0.87
    erton
    -0.85
    )=(
    -0.81
    erer
    -0.81
    ãģ¦
    -0.79
    utable
    -0.77
    raltar
    -0.76
    omsday
    -0.76
    POSITIVE LOGITS
     Genocide
    1.11
     Apost
    0.91
     genocide
    0.76
     Airlines
    0.73
     Armenian
    0.71
    beit
    0.69
     agre
    0.68
    inian
    0.65
     NOTICE
    0.62
     Azerbai
    0.61
    Activations Density 0.017%

    No Known Activations