© 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. 4885
    Prev
    Next
    INDEX
    Explanations

    details related to racial disparities and policies aimed at addressing them

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

    phrases related to political representation and community engagement

    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
    border
    -0.80
     notebooks
    -0.77
     declass
    -0.74
     coils
    -0.70
    Border
    -0.69
     malt
    -0.67
     Wildcats
    -0.66
     vert
    -0.65
     Patent
    -0.65
    dit
    -0.64
    POSITIVE LOGITS
    Mayor
    2.22
     Mayor
    2.11
     mayoral
    2.08
     mayor
    2.02
    City
    1.99
     City
    1.93
     city
    1.92
    Council
    1.92
     mayors
    1.71
     councillors
    1.71
    Activations Density 0.757%

    No Known Activations