© 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. 2-RES-JB
    11. 9092
    Prev
    Next
    INDEX
    Explanations

    mentions of security-related terms, especially related to airport security such as TSA and scanners

    oai_token-act-pair · gpt-3.5-turbo

    references to governmental agencies related to security and their related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥł
    -0.78
    hips
    -0.75
    taboola
    -0.74
    ÑĮ
    -0.73
     Lazarus
    -0.68
    mobi
    -0.67
    orthern
    -0.67
    makers
    -0.66
    à¼
    -0.64
    oubt
    -0.64
    POSITIVE LOGITS
     TSA
    1.04
     checkpoint
    0.77
    heed
    0.77
     checkpoints
    0.77
    igger
    0.71
     brass
    0.70
    rette
    0.70
     clearance
    0.69
     bureaucracy
    0.69
    enei
    0.68
    Activations Density 0.010%

    No Known Activations