© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 4744
    Prev
    Next
    INDEX
    Explanations

    information related to military actions or missile launches, particularly in North Korea

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    information related to military actions and nuclear capabilities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moroccan
    -0.94
     Wenger
    -0.84
     Quebec
    -0.84
    ér
    -0.84
     Montreal
    -0.82
     Morocco
    -0.80
     Giul
    -0.80
    udic
    -0.79
     Bosnia
    -0.78
    Italy
    -0.77
    POSITIVE LOGITS
     Korean
    1.25
     DPRK
    1.15
     Pyongyang
    1.08
     Korea
    1.07
     Kore
    1.06
     Koreans
    1.05
     Seoul
    1.05
     peninsula
    1.04
    Py
    1.04
     Jong
    0.99
    Activations Density 0.168%

    No Known Activations