© 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. 3036
    Prev
    Next
    INDEX
    Explanations

    phrases that express surprise or disbelief

    oai_token-act-pair · gpt-3.5-turbo

    expressions of disbelief or surprise

    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
     guiActiveUnfocused
    -0.80
    20439
    -0.71
     Reprodu
    -0.70
     Springer
    -0.69
    enthal
    -0.69
     mosqu
    -0.69
    ously
    -0.68
    creen
    -0.64
    eer
    -0.64
     association
    -0.63
    POSITIVE LOGITS
    ª
    1.09
    ł
    1.07
    IJ
    0.95
    Ĵ
    0.94
    ij
    0.92
    ı
    0.91
    once
    0.90
    «
    0.89
    ¹
    0.87
    »
    0.87
    Activations Density 0.186%

    No Known Activations