© 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. 11121
    Prev
    Next
    INDEX
    Explanations

    terms related to weapons and international trade of commodities

    oai_token-act-pair · gpt-3.5-turbo

    terms related to arms and military supplies as well as food production

    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
    enegger
    -0.78
     Comedy
    -0.75
     Beard
    -0.73
     amused
    -0.72
     Monstrous
    -0.71
    renheit
    -0.69
     Kids
    -0.69
     Spiritual
    -0.67
     Werewolf
    -0.66
     Toast
    -0.66
    POSITIVE LOGITS
     smuggling
    1.30
     trafficking
    1.19
     shipments
    1.15
     exports
    1.15
     redistribution
    1.11
     scarcity
    1.10
     exporting
    1.09
     shortages
    1.08
     export
    1.07
    grab
    1.06
    Activations Density 0.222%

    No Known Activations