© 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. 10-RES-JB
    11. 24290
    Prev
    Next
    INDEX
    Explanations

    terms related to customs, border protection, and regulatory bodies

    oai_token-act-pair · gpt-3.5-turbo

    mentions of customs and border protection agencies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ynasty
    -0.68
    enegger
    -0.66
    vironment
    -0.66
    itsch
    -0.65
     Bib
    -0.64
    bler
    -0.64
     Paraly
    -0.62
     Zed
    -0.61
     Moonlight
    -0.61
     TAMADRA
    -0.61
    POSITIVE LOGITS
     Enforcement
    1.05
     inspectors
    0.97
     Customs
    0.92
    enforcement
    0.91
     customs
    0.90
     officers
    0.88
     agents
    0.88
     Agents
    0.86
     inspections
    0.83
     enforcement
    0.83
    Activations Density 0.053%

    No Known Activations