© 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. 10-RES-JB
    11. 16580
    Prev
    Next
    INDEX
    Explanations

    instances where someone is surprised or amazed by a particular event or revelation

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief

    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
     hemor
    -0.69
    interstitial
    -0.60
     bona
    -0.60
    osi
    -0.59
     Annotations
    -0.58
    bern
    -0.58
    accompan
    -0.58
     assum
    -0.58
    ilon
    -0.58
    winner
    -0.57
    POSITIVE LOGITS
     how
    0.95
     by
    0.75
     surprised
    0.74
     seeing
    0.74
     when
    0.67
    how
    0.67
     aback
    0.67
     discover
    0.65
     amaz
    0.64
     HOW
    0.64
    Activations Density 0.061%

    No Known Activations