© 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. 2-RES-JB
    11. 23792
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Prince"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of royalty, specifically the title "Prince."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fram
    -0.67
    ************
    -0.66
     Bulletin
    -0.64
    trak
    -0.64
     ledger
    -0.63
     drawer
    -0.62
     Locked
    -0.61
    early
    -0.61
    ¶
    -0.60
     clipboard
    -0.60
    POSITIVE LOGITS
     Prince
    1.02
    Prince
    0.92
    doms
    0.90
    cipled
    0.81
     Rupert
    0.80
    loo
    0.80
     Bride
    0.80
    VPN
    0.76
     Hood
    0.75
    inho
    0.74
    Activations Density 0.010%

    No Known Activations