© 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. 10-RES-JB
    11. 3112
    Prev
    Next
    INDEX
    Explanations

    mentions of showcasing or displaying items

    oai_token-act-pair · gpt-3.5-turbo

    instances of showing off or showcasing something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imester
    -0.88
    quickShipAvailable
    -0.86
     msec
    -0.81
    ANCE
    -0.79
    xiety
    -0.75
    terness
    -0.74
    eter
    -0.73
    legraph
    -0.73
    endez
    -0.72
    displayText
    -0.70
    POSITIVE LOGITS
     newest
    1.19
     goodies
    1.11
     prototypes
    1.05
     creations
    1.04
     new
    1.03
     gear
    1.02
     toys
    1.02
     gadgets
    1.01
     shiny
    1.00
     chops
    0.99
    Activations Density 0.500%

    No Known Activations