© 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. 8-RES-JB
    11. 11443
    Prev
    Next
    INDEX
    Explanations

    words related to being surprised or closely observing a situation

    oai_token-act-pair · gpt-3.5-turbo

    words related to surprise or unexpected events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rongh
    -0.61
     Maxwell
    -0.58
     perspective
    -0.57
     Zionism
    -0.56
     limp
    -0.55
     Scully
    -0.55
     Gaul
    -0.55
     Whitman
    -0.54
     skate
    -0.54
     brains
    -0.54
    POSITIVE LOGITS
    illance
    0.87
    illes
    0.72
    ê
    0.71
    cliffe
    0.70
     COURT
    0.70
    Capture
    0.69
    Downloadha
    0.68
    ENTION
    0.66
    fit
    0.66
    âĶĢâĶĢâĶĢâĶĢ
    0.66
    Activations Density 0.062%

    No Known Activations