© 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. 8-RES-JB
    11. 20423
    Prev
    Next
    INDEX
    Explanations

    strong emotional reactions such as shock, surprise, or amazement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of surprise or shock

    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
    •layer 8 - surprise

    No Comments

    Negative Logits
     forearm
    -0.65
    uben
    -0.65
    omo
    -0.64
     slips
    -0.64
    porary
    -0.63
    illusion
    -0.62
     extracted
    -0.61
     stake
    -0.61
    vil
    -0.60
     redistributed
    -0.59
    POSITIVE LOGITS
    ingly
    1.10
     onlook
    1.04
     us
    0.94
     me
    0.93
     him
    0.86
     investigators
    0.77
    udic
    0.77
     audiences
    0.76
     commenters
    0.75
     readers
    0.73
    Activations Density 0.167%

    No Known Activations