© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 3-RES-JB
    6. 3282
    Prev
    Next
    INDEX
    Explanations

    expressions of astonishment or excitement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    expressions or phrases denoting amazement or surprise

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •layer 3 - surprise

    No Comments

    Negative Logits
    andro
    -0.76
    ":[{"
    -0.75
    */(
    -0.72
    ugal
    -0.70
     kindred
    -0.68
    rupulous
    -0.67
     delinqu
    -0.67
    unal
    -0.67
    responsible
    -0.65
    rio
    -0.65
    POSITIVE LOGITS
     Wow
    1.05
    ards
    0.96
    zers
    0.92
    Wow
    0.90
    orld
    0.89
    wow
    0.83
     wow
    0.81
    herty
    0.78
    !/
    0.76
    biz
    0.75
    Activations Density 0.009%

    No Known Activations