© 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. 9-RES-JB
    11. 15726
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographic locations

    oai_token-act-pair · gpt-3.5-turbo

    names of geographic locations and associated terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.87
    ntil
    -0.86
    undo
    -0.82
    PROV
    -0.80
    PDATE
    -0.80
    emonic
    -0.76
    udic
    -0.76
    externalActionCode
    -0.74
    soDeliveryDate
    -0.73
    accompan
    -0.70
    POSITIVE LOGITS
    shire
    1.53
     Manor
    1.04
     Borough
    0.97
     Spit
    0.94
     Junction
    0.92
     Heath
    0.90
     Hills
    0.90
     Mansion
    0.88
    hurst
    0.85
     Mills
    0.85
    Activations Density 0.137%

    No Known Activations