© 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. 6-RES-JB
    11. 1078
    Prev
    Next
    INDEX
    Explanations

    the word "surprise"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "surprise" and its variants

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ©¶æ
    -0.96
    bis
    -0.82
    İĭ
    -0.82
    nan
    -0.81
    asus
    -0.80
    ssl
    -0.79
    oreal
    -0.77
    everal
    -0.75
    agra
    -0.74
    oran
    -0.74
    POSITIVE LOGITS
     surprise
    0.90
     surprises
    0.88
     Surprise
    0.87
    ingly
    0.85
     Flavoring
    0.74
    ously
    0.72
    Berry
    0.71
     onlook
    0.69
     absor
    0.68
     Pon
    0.68
    Activations Density 0.028%

    No Known Activations