© 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. 4993
    Prev
    Next
    INDEX
    Explanations

    phrases related to social and political discourse

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

    discussions surrounding individual rights and responsibilities within societal structures

    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
     crooked
    -0.78
     swell
    -0.77
     Grill
    -0.74
     pave
    -0.73
     pound
    -0.72
     peel
    -0.72
     paddle
    -0.72
     Dull
    -0.71
     Peb
    -0.71
     Tall
    -0.70
    POSITIVE LOGITS
    education
    1.50
    social
    1.48
    environment
    1.46
    community
    1.46
    politics
    1.45
    science
    1.45
    consumer
    1.43
    technology
    1.43
    development
    1.43
    knowledge
    1.41
    Activations Density 0.468%

    No Known Activations