© 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 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. 10-RES-JB
    11. 5994
    Prev
    Next
    INDEX
    Explanations

    information related to government resolutions and community development in specific regions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific years and legislative actions

    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
    ettel
    -1.09
     Bundesliga
    -1.02
     Ferrari
    -0.99
    ueller
    -0.98
     Carlo
    -0.91
    Italy
    -0.91
    iquid
    -0.90
    erno
    -0.89
     Dresden
    -0.89
     Frankfurt
    -0.88
    POSITIVE LOGITS
     Navajo
    2.09
     Native
    1.92
     Indigenous
    1.82
    Native
    1.80
     Aboriginal
    1.76
     tribe
    1.76
     Tribal
    1.75
     tribal
    1.75
     tribes
    1.68
     aboriginal
    1.64
    Activations Density 0.319%

    No Known Activations