© 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. 10-RES-JB
    11. 14187
    Prev
    Next
    INDEX
    Explanations

    information related to weapons testing and international relations, particularly concerning North Korea

    oai_token-act-pair · gpt-3.5-turbo

    references to nuclear testing and related geopolitical tensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ̶
    -0.98
     Giul
    -0.96
     Parm
    -0.95
     Ambro
    -0.91
     Lara
    -0.89
     Gallagher
    -0.86
    <?
    -0.85
     Wenger
    -0.84
     ASP
    -0.84
    udic
    -0.82
    POSITIVE LOGITS
     Pyongyang
    2.10
     DPRK
    1.93
     Seoul
    1.75
     Korea
    1.72
     Korean
    1.71
     Jong
    1.68
    ongyang
    1.64
     Kim
    1.61
     Koreans
    1.60
     NK
    1.49
    Activations Density 0.357%

    No Known Activations