© 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. 1-RES-JB
    11. 14595
    Prev
    Next
    INDEX
    Explanations

    words related to places or locations, specifically focusing on mentions of "New York"

    oai_token-act-pair · gpt-3.5-turbo

    references to the state of New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.80
    poke
    -0.79
    warts
    -0.78
    arching
    -0.78
    uddin
    -0.77
     actionGroup
    -0.75
    byss
    -0.74
    ï¸ı
    -0.73
    Reloaded
    -0.73
    ascript
    -0.73
    POSITIVE LOGITS
     York
    1.39
     Zealand
    1.23
     Orleans
    1.19
     Hampshire
    1.18
     Yorker
    1.16
     Jersey
    1.15
     Yorkers
    1.06
     Brunswick
    1.00
     YORK
    0.97
    foundland
    0.93
    Activations Density 0.050%

    No Known Activations