© 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. 4903
    Prev
    Next
    INDEX
    Explanations

    historical events and historical figures

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

    the word "undeniably."

    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
     gorilla
    -0.79
     scraping
    -0.72
     fart
    -0.68
     coughing
    -0.66
     understatement
    -0.66
     bargaining
    -0.65
     widening
    -0.62
     domains
    -0.61
     dealing
    -0.61
    ÙIJ
    -0.61
    POSITIVE LOGITS
    ocumented
    1.59
    ecided
    1.51
    etermined
    1.50
    oubtedly
    1.50
    iscovered
    1.50
    efeated
    1.49
    efined
    1.44
    ifferent
    1.42
    oubted
    1.41
    rafted
    1.40
    Activations Density 0.024%

    No Known Activations