© 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. 4836
    Prev
    Next
    INDEX
    Explanations

    references to a specific name "Jason", possibly emphasizing mentions or actions related to individuals named Jason

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

    occurrences of the name "Jason"

    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
    minist
    -0.76
    iments
    -0.68
     conducive
    -0.67
    Reviewer
    -0.66
    gra
    -0.63
     showc
    -0.62
     material
    -0.62
     plur
    -0.62
    ega
    -0.61
     exerc
    -0.60
    POSITIVE LOGITS
     Chaff
    1.19
     Kidd
    1.07
     Blossom
    0.94
     Bour
    0.88
     Collins
    0.88
     Kessler
    0.87
     Johann
    0.87
     Fur
    0.87
     Cummings
    0.84
     Garrison
    0.83
    Activations Density 0.013%

    No Known Activations