© 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. 10-RES-JB
    11. 11202
    Prev
    Next
    INDEX
    Explanations

    mentions of political figures, government departments, and locations related to Maryland

    oai_token-act-pair · gpt-3.5-turbo

    references to political figures and government officials, particularly from Maryland

    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
     Finnish
    -1.30
    Japan
    -1.21
    Japanese
    -1.21
     Finland
    -1.21
    ä
    -1.20
    ö
    -1.18
    Brazil
    -1.15
     Indones
    -1.15
     Kyoto
    -1.14
     Japan
    -1.14
    POSITIVE LOGITS
     Maryland
    1.80
    Baltimore
    1.72
     Baltimore
    1.68
     Virginia
    1.46
     Md
    1.43
    Virginia
    1.41
    uliffe
    1.34
     Ravens
    1.28
     McAuliffe
    1.27
     Freddie
    1.26
    Activations Density 0.159%

    No Known Activations