© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    government and political related terms, such as government positions, organizations and political events

    oai_token-act-pair · gpt-3.5-turbo

    references to political and government figures and organizations

    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
     Robots
    -0.88
    packs
    -0.85
     iPads
    -0.83
    ramids
    -0.81
     robots
    -0.80
     Machines
    -0.79
    devices
    -0.78
    illions
    -0.77
    adoes
    -0.77
     vans
    -0.77
    POSITIVE LOGITS
     official
    1.34
     ally
    1.33
     figure
    1.25
     diplomat
    1.22
     operative
    1.22
     adviser
    1.19
     staffer
    1.18
     negotiator
    1.18
     aide
    1.18
     insider
    1.17
    Activations Density 0.210%

    No Known Activations