© 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. 6-RES-JB
    11. 17583
    Prev
    Next
    INDEX
    Explanations

    references to political and military activities related to North Korea

    oai_token-act-pair · gpt-3.5-turbo

    mentions of North Korea

    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
    igue
    -0.85
    ++++++++++++++++
    -0.80
    MENTS
    -0.77
    llo
    -0.75
    gerald
    -0.70
    Baltimore
    -0.69
    Mouse
    -0.67
    ments
    -0.66
     Wond
    -0.66
    MENT
    -0.65
    POSITIVE LOGITS
    orea
    1.00
     defect
    0.86
     blackmail
    0.83
     Pyongyang
    0.81
    ongyang
    0.80
     meltdown
    0.80
     detonated
    0.79
     Koreans
    0.78
     Korea
    0.78
     ì
    0.77
    Activations Density 0.029%

    No Known Activations