© 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. 6721
    Prev
    Next
    INDEX
    Explanations

    geographic locations, particularly in different continents

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, particularly South and North America

    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
     ranger
    -0.71
    inventoryQuantity
    -0.68
     glim
    -0.64
    orget
    -0.63
    inel
    -0.62
     tee
    -0.62
     sniper
    -0.61
    inator
    -0.61
    hess
    -0.61
    aminer
    -0.60
    POSITIVE LOGITS
     Africa
    1.44
     Asia
    1.29
     America
    1.18
     Arabia
    1.16
     Europe
    1.16
     Korea
    1.13
    thia
    1.09
    asia
    1.05
     Sudan
    1.00
     Lanka
    1.00
    Activations Density 0.072%

    No Known Activations