© 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. 0-RES-JB
    11. 5029
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating surprise or unexpectedness

    oai_token-act-pair · gpt-3.5-turbo

    the word "surprisingly" and its variants to highlight unexpected situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 0 - surprise

    No Comments

    Negative Logits
    pri
    -0.67
    onge
    -0.66
    OWN
    -0.64
    eur
    -0.64
    gate
    -0.62
    rient
    -0.61
    parent
    -0.58
    mer
    -0.58
    ourn
    -0.57
    itives
    -0.57
    POSITIVE LOGITS
     surprisingly
    3.39
     shockingly
    2.36
     remarkably
    2.25
     unsurprisingly
    2.16
     predictably
    1.80
    surprisingly
    1.79
     amazingly
    1.76
     strangely
    1.75
     curiously
    1.66
     unexpectedly
    1.64
    Activations Density 0.029%

    No Known Activations