© 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. 11-RES-JB
    11. 22329
    Prev
    Next
    INDEX
    Explanations

    the names of towns and cities with an emphasis on geographical locations

    oai_token-act-pair · gpt-3.5-turbo

    references to specific towns, cities, and geographical locations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inventoryQuantity
    -0.73
    prints
    -0.70
     Decay
    -0.67
    cycle
    -0.65
    adders
    -0.63
    ombies
    -0.60
    urations
    -0.59
    sers
    -0.58
     Clockwork
    -0.58
     bandwagon
    -0.58
    POSITIVE LOGITS
     northeast
    1.25
     southwest
    1.24
     northwest
    1.24
     bordering
    1.23
     southeast
    1.17
     near
    1.12
     overlooking
    1.08
     tucked
    1.06
     situated
    1.05
     south
    1.04
    Activations Density 0.273%

    No Known Activations