© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 17411
    Prev
    Next
    INDEX
    Explanations

    surprise-related words and phrases

    oai_token-act-pair · gpt-3.5-turbo

    references to unexpected events or outcomes

    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
    tein
    -1.09
    folios
    -1.03
    burgh
    -0.91
    İĭ
    -0.80
    hetically
    -0.79
    oran
    -0.76
    nan
    -0.76
    rx
    -0.75
    asus
    -0.73
    eworks
    -0.73
    POSITIVE LOGITS
     arrival
    0.93
     surprise
    0.87
     visitor
    0.87
     surprises
    0.86
     unexpected
    0.85
     guests
    0.83
     Guest
    0.78
     twists
    0.77
     guest
    0.73
     revelation
    0.73
    Activations Density 0.089%

    No Known Activations