© 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. 6-RES-JB
    11. 14477
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of surprise

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "sur."

    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
    •layer 6 - surprise

    No Comments

    Negative Logits
    icals
    -0.78
    itsch
    -0.73
    ICAL
    -0.73
    opathic
    -0.72
    ioch
    -0.67
    OWN
    -0.65
    naires
    -0.64
     tense
    -0.62
    opathy
    -0.62
     Pax
    -0.62
    POSITIVE LOGITS
    mounted
    1.12
    mount
    1.04
    fer
    1.01
    geons
    0.95
    geon
    0.94
    rounded
    0.92
    lation
    0.90
    charge
    0.87
    lim
    0.86
    vey
    0.85
    Activations Density 0.009%

    No Known Activations