© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 723
    Prev
    Next
    INDEX
    Explanations

    terms related to urban planning and infrastructure, specifically focusing on transportation projects and initiatives

    oai_token-act-pair · gpt-3.5-turbo

    references to transportation concepts and issues

    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
    --+
    -0.71
    sonian
    -0.70
    monds
    -0.69
    ellen
    -0.68
    ividual
    -0.67
    quist
    -0.65
    kai
    -0.65
    gling
    -0.64
    sembly
    -0.64
    anova
    -0.62
    POSITIVE LOGITS
     hubs
    1.03
     infrastructure
    0.97
     planners
    0.88
     Infrastructure
    0.86
     corridors
    0.84
     routes
    0.84
     logistics
    0.83
     transportation
    0.81
     vehicles
    0.78
    Safety
    0.78
    Activations Density 0.035%

    No Known Activations