© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 4159
    Prev
    Next
    INDEX
    Explanations

    phrases related to military discussions and international affairs

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

    references to international relations and defense policies

    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
     Printed
    -0.75
     Celeb
    -0.74
     Reincarn
    -0.73
    utenberg
    -0.72
     Parking
    -0.67
     Inher
    -0.67
     Manson
    -0.66
     Sparks
    -0.65
     Dise
    -0.64
     Rabbit
    -0.64
    POSITIVE LOGITS
     counterterrorism
    1.39
     diplomacy
    1.22
     diplomatic
    1.09
     NATO
    1.04
     bilateral
    1.01
     interoper
    1.00
     partnerships
    0.99
     partners
    0.99
     ISIL
    0.98
     alliances
    0.98
    Activations Density 0.457%

    No Known Activations