© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RES-JB
    11. 11259
    Prev
    Next
    INDEX
    Explanations

    mentions of international trade agreements and partnerships

    oai_token-act-pair · gpt-3.5-turbo

    topics related to trade agreements and economic policies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hubbard
    -1.02
     Slay
    -0.78
     Darrell
    -0.78
     Buster
    -0.75
     Betty
    -0.74
     Pasadena
    -0.72
     Vaughn
    -0.72
     Kyl
    -0.72
     Hitchcock
    -0.71
     Ralph
    -0.71
    POSITIVE LOGITS
     exports
    1.21
     imports
    0.98
     envoy
    0.91
     visas
    0.90
     trade
    0.85
     export
    0.85
     visa
    0.83
     exporting
    0.83
     diplomacy
    0.83
    export
    0.83
    Activations Density 0.270%

    No Known Activations