© 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. 2-RES-JB
    11. 9201
    Prev
    Next
    INDEX
    Explanations

    phrases 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 @ 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
    ++++++++++++++++
    -0.75
    Tags
    -0.75
     Wally
    -0.72
     Henri
    -0.69
    VID
    -0.69
    brand
    -0.68
    eight
    -0.67
    vol
    -0.65
     Ralph
    -0.64
    Rober
    -0.64
    POSITIVE LOGITS
    orea
    1.04
     Korea
    0.88
    ese
    0.82
     DPR
    0.82
    ongyang
    0.73
     meltdown
    0.73
     Jong
    0.72
     DPRK
    0.72
     readiness
    0.72
     consulate
    0.72
    Activations Density 0.023%

    No Known Activations