© 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. 7-RES-JB
    11. 12456
    Prev
    Next
    INDEX
    Explanations

    references to a specific person named Kim Jong

    oai_token-act-pair · gpt-3.5-turbo

    references to Kim Jong Un and related figures

    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
    rawdownloadcloneembedreportprint
    -0.79
    ANT
    -0.74
    ATTLE
    -0.69
    arians
    -0.69
    WORK
    -0.69
    Results
    -0.67
    VID
    -0.67
    MENTS
    -0.65
    antic
    -0.65
    BACK
    -0.64
    POSITIVE LOGITS
    ongyang
    1.01
    sung
    0.92
     Jong
    0.90
     Suk
    0.83
    unta
    0.81
    resy
    0.81
    jong
    0.77
     Jinping
    0.77
    lasses
    0.77
    jri
    0.77
    Activations Density 0.016%

    No Known Activations