© 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. 20755
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures and related geopolitical events

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and their roles

    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
     Charleston
    -1.00
     Holden
    -0.99
     IBM
    -0.99
     Corvette
    -0.91
     Worcester
    -0.87
     Vermont
    -0.86
     Payton
    -0.84
     Blacks
    -0.83
    wb
    -0.81
     VMware
    -0.80
    POSITIVE LOGITS
     Ankara
    2.50
     Erdogan
    2.36
     Turkish
    2.32
    Turkey
    2.28
    Turkish
    2.27
     Turkey
    2.23
     Istanbul
    2.12
    ÄŁ
    2.09
     PKK
    2.06
     Recep
    2.03
    Activations Density 0.362%

    No Known Activations