© 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. 9978
    Prev
    Next
    INDEX
    Explanations

    adverbs that convey surprise or unexpectedness

    oai_token-act-pair · gpt-3.5-turbo

    the word "surprisingly" and its variants to highlight unexpected results or observations

    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
    icip
    -0.78
    arta
    -0.72
    flight
    -0.71
    icipated
    -0.68
    lord
    -0.62
    gang
    -0.62
     Players
    -0.62
    orem
    -0.60
    rike
    -0.60
    uese
    -0.60
    POSITIVE LOGITS
    beit
    0.82
     situated
    0.80
     LIMITED
    0.79
     absent
    0.78
     impressive
    0.71
     shaped
    0.71
     uncomfortable
    0.70
    STEM
    0.69
     Pengu
    0.68
     dull
    0.68
    Activations Density 0.047%

    No Known Activations