© 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. 8-RES-JB
    11. 3361
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations, specifically focusing on areas near lakes and cities

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographic locations, specifically places with "Lake" or "City" in their name

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enegger
    -0.78
    schild
    -0.74
     streng
    -0.71
    gets
    -0.67
    mble
    -0.67
     behavi
    -0.66
    GES
    -0.62
    ilater
    -0.62
    atson
    -0.60
    bye
    -0.60
    POSITIVE LOGITS
     City
    1.10
     Springs
    0.92
     Tribune
    0.89
    apolis
    0.84
    pi
    0.83
     Falls
    0.82
    City
    0.80
     Arabia
    0.77
     Rapids
    0.76
    adelphia
    0.75
    Activations Density 0.027%

    No Known Activations