© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 20104
    Prev
    Next
    INDEX
    Explanations

    references to royalty or majestic figures

    oai_token-act-pair · gpt-3.5-turbo

    references to monarchs and monarchies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rudy
    -0.73
     Soda
    -0.70
    ICE
    -0.69
     firing
    -0.69
     Pixel
    -0.68
     SIM
    -0.67
     Sang
    -0.66
    bu
    -0.65
     Hig
    -0.64
    bang
    -0.64
    POSITIVE LOGITS
     monarch
    3.89
     monarchy
    2.64
     Monarch
    2.50
     kings
    1.50
     butterflies
    1.41
     queens
    1.39
     royal
    1.38
     queen
    1.35
     king
    1.34
     roy
    1.34
    Activations Density 0.020%

    No Known Activations