© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12721
    Prev
    Next
    INDEX
    Explanations

    words related to specific locations and events in different regions

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and their affiliations

    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
    Wilson
    -0.79
    quickShipAvailable
    -0.70
    writers
    -0.70
    ullivan
    -0.68
    inventoryQuantity
    -0.68
    Jones
    -0.66
     Paige
    -0.66
    sheet
    -0.65
    Denver
    -0.62
    writer
    -0.62
    POSITIVE LOGITS
     Province
    1.54
     province
    1.48
     Pradesh
    1.22
     Municip
    1.20
     Peninsula
    1.18
     peninsula
    1.16
     County
    1.15
     municipality
    1.13
     countryside
    1.12
     region
    1.09
    Activations Density 0.173%

    No Known Activations