Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 23604
    Prev
    Next
    INDEX
    Explanations

    words related to wonder or amazement

    oai_token-act-pair · gpt-3.5-turbo

    expressions of awe or amazement

    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
    rams
    -0.77
    IDs
    -0.68
     Rosa
    -0.68
    bourg
    -0.66
    IP
    -0.64
     Giuliani
    -0.63
    idal
    -0.63
    portation
    -0.63
    IDE
    -0.63
     Minority
    -0.62
    POSITIVE LOGITS
     aw
    3.96
    Aw
    1.51
     AW
    1.42
     Aw
    1.38
    awk
    1.19
     awaken
    1.17
    aw
    1.15
    AW
    1.14
     amaz
    1.09
     awa
    1.09
    Activations Density 0.019%

    No Known Activations