© 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 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. 17678
    Prev
    Next
    INDEX
    Explanations

    instances where the text expresses surprise or being surprised

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "surprised" in various contexts

    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
    -0.77
    interstitial
    -0.73
    ngth
    -0.73
    ciplinary
    -0.72
    amins
    -0.72
    bern
    -0.70
    utf
    -0.70
    ignty
    -0.70
    itte
    -0.68
    haar
    -0.67
    POSITIVE LOGITS
     Squid
    0.71
     enough
    0.71
    vale
    0.69
    ãĤ¦ãĤ¹
    0.69
     aback
    0.67
     Pew
    0.67
    >>>
    0.67
    cules
    0.65
     how
    0.65
     Dragonbound
    0.64
    Activations Density 0.029%

    No Known Activations