© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    6. 20418
    Prev
    Next
    INDEX
    Explanations

    words related to states of being amazed or gazes of admiration

    oai_token-act-pair · gpt-3.5-turbo

    words related to amazement or astonishment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     err
    -0.69
     necess
    -0.67
     ant
    -0.67
     prostitutes
    -0.61
     gener
    -0.60
     export
    -0.60
    pring
    -0.60
     Lib
    -0.60
     Esp
    -0.60
     reprint
    -0.60
    POSITIVE LOGITS
    azed
    4.02
    azing
    3.02
    azes
    1.91
    aze
    1.49
    azer
    1.11
    bitious
    1.11
    affles
    0.98
    usters
    0.98
    ummies
    0.93
    rugged
    0.91
    Activations Density 0.013%

    No Known Activations