© 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 EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12189
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise or disbelief involving the phrase "Oh my god" or similar variations

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or disbelief, particularly involving variations of "oh my god/goodness."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 11 - surprise

    No Comments

    Negative Logits
    ierrez
    -0.70
    entary
    -0.69
    ributed
    -0.68
    nell
    -0.65
    ighthouse
    -0.64
    vable
    -0.64
    iris
    -0.63
    inelli
    -0.61
    orea
    -0.61
    aying
    -0.60
    POSITIVE LOGITS
     god
    1.31
     goodness
    1.30
     heavens
    1.26
     GOD
    1.16
    god
    1.15
     God
    1.08
     Merlin
    1.07
     fuck
    1.07
     heaven
    1.06
     hell
    1.06
    Activations Density 0.110%

    No Known Activations