© 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. 11-RES-JB
    11. 20764
    Prev
    Next
    INDEX
    Explanations

    words related to international politics and diplomacy

    oai_token-act-pair · gpt-3.5-turbo

    references to international political actions and dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
     glim
    -0.85
    maxwell
    -0.78
    natureconservancy
    -0.74
    enfranch
    -0.70
    alach
    -0.68
     ILCS
    -0.67
    ministic
    -0.64
     clutter
    -0.64
    å°Ĩ
    -0.62
    itialized
    -0.62
    POSITIVE LOGITS
     Islamabad
    1.18
     Nato
    1.18
     Ankara
    1.15
     Lavrov
    1.08
     Riyadh
    1.08
    Moscow
    1.08
     Moscow
    1.07
     diplomatic
    1.04
     diplomats
    1.01
     Tehran
    1.00
    Activations Density 0.414%

    No Known Activations