© 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. 13502
    Prev
    Next
    INDEX
    Explanations

    sentences expressing surprise or astonishment

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating surprise or astonishment

    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
    alach
    -0.78
    enture
    -0.75
    reau
    -0.75
     condu
    -0.70
     conduit
    -0.68
    illes
    -0.67
    uti
    -0.67
    aim
    -0.65
     vend
    -0.61
     qui
    -0.60
    POSITIVE LOGITS
    DERR
    0.84
     surprise
    0.73
    IGHT
    0.72
    iry
    0.67
     how
    0.67
    ãĥ©ãĥ³
    0.62
     headlines
    0.61
    Appearance
    0.61
     seeing
    0.59
     [*
    0.59
    Activations Density 0.210%

    No Known Activations