© 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. 0-RES-JB
    11. 7973
    Prev
    Next
    INDEX
    Explanations

    mentions of international organizations such as "United Nations"

    oai_token-act-pair · gpt-3.5-turbo

    references to nations and their organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vac
    -0.67
     sle
    -0.65
     mol
    -0.62
     notebook
    -0.61
     slightly
    -0.60
     cavity
    -0.60
    plin
    -0.59
    bot
    -0.59
     setup
    -0.59
     magnetic
    -0.59
    POSITIVE LOGITS
     Nations
    4.06
     Nation
    1.83
     nations
    1.74
     States
    1.66
     Countries
    1.57
    States
    1.45
     Governments
    1.23
     Races
    1.20
    Nation
    1.19
     STATES
    1.18
    Activations Density 0.015%

    No Known Activations