© 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. 7-RES-JB
    11. 8442
    Prev
    Next
    INDEX
    Explanations

    instances where someone is surprised

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 7 - surprise

    No Comments

    Negative Logits
    alach
    -0.82
    ngth
    -0.76
    href
    -0.74
    obe
    -0.70
    bern
    -0.70
    utf
    -0.70
    ciplinary
    -0.70
    itte
    -0.70
    iffe
    -0.69
    tein
    -0.69
    POSITIVE LOGITS
     enough
    0.77
     how
    0.76
     aback
    0.73
     Squid
    0.70
    ãĤ¦ãĤ¹
    0.69
     Pew
    0.69
    cules
    0.69
     Howell
    0.65
     Robin
    0.64
    090
    0.64
    Activations Density 0.036%

    No Known Activations