© 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. 7-RES-JB
    11. 1793
    Prev
    Next
    INDEX
    Explanations

    surprising or amazed reactions in text

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express surprise or unexpectedness

    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
    Not in Any Lists

    No Comments

    Negative Logits
    burgh
    -0.80
    illes
    -0.67
     bye
    -0.66
     throats
    -0.66
    aim
    -0.62
    ère
    -0.61
    alach
    -0.60
    ulton
    -0.59
    Recommended
    -0.59
     fid
    -0.59
    POSITIVE LOGITS
     similarities
    0.81
     how
    0.70
     similarity
    0.69
     discrepancies
    0.68
    fusc
    0.67
    how
    0.65
     Conserv
    0.64
     unanim
    0.64
     parallels
    0.64
     surprise
    0.64
    Activations Density 0.239%

    No Known Activations