© 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. 5053
    Prev
    Next
    INDEX
    Explanations

    names of individuals known as celebrities

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

    mentions of the name "Billy" in various contexts

    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
    ally
    -0.74
    ually
    -0.71
    aries
    -0.68
    ALLY
    -0.66
    eus
    -0.65
    arily
    -0.65
    ational
    -0.63
    ATING
    -0.62
     commons
    -0.62
    ately
    -0.61
    POSITIVE LOGITS
     Idol
    0.95
    xtap
    0.95
     Goat
    0.90
     Pilgrim
    0.87
     Joel
    0.84
    cock
    0.81
     Gunn
    0.81
     Meier
    0.80
     Crystal
    0.80
     Graham
    0.79
    Activations Density 0.024%

    No Known Activations