© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 12-RES-JB
    11. 5071
    Prev
    Next
    INDEX
    Explanations

    phrases related to geopolitical events and governmental actions

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    occurrences of the word "the."

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    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_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    TION
    -1.00
    }}}
    -0.77
    inventoryQuantity
    -0.70
    enegger
    -0.70
    vich
    -0.68
    soDeliveryDate
    -0.67
    issance
    -0.63
    verson
    -0.63
    ))))
    -0.62
    TING
    -0.62
    POSITIVE LOGITS
     forefront
    1.27
     table
    1.20
     realization
    1.19
     rescue
    1.16
     attention
    1.14
     conclusion
    1.12
     shores
    1.02
     doorstep
    1.02
     fold
    0.99
     senses
    0.97
    Activations Density 0.172%

    No Known Activations