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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 5652
    Prev
    Next
    INDEX
    Explanations

    locations or buildings with the word "Palace."

    oai_token-act-pair · gpt-3.5-turbo

    mentions of various palaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    schild
    -0.75
    ï¸ı
    -0.68
    err
    -0.68
    REE
    -0.68
    rss
    -0.67
    EMP
    -0.67
    rd
    -0.66
    CAST
    -0.66
    ACTED
    -0.65
    LER
    -0.65
    POSITIVE LOGITS
     Palace
    0.87
    ibur
    0.78
    monary
    0.77
    osaurs
    0.76
    gur
    0.74
     intrigue
    0.74
     Hotel
    0.74
     entrances
    0.72
     intrig
    0.72
     maiden
    0.71
    Activations Density 0.017%

    No Known Activations