© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 14827
    Prev
    Next
    INDEX
    Explanations

    requests or instructions in the form of the word "Please."

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Please"

    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
     acquired
    -0.67
     intangible
    -0.67
     architect
    -0.64
     established
    -0.63
     attributes
    -0.63
    lier
    -0.62
     early
    -0.62
     wound
    -0.62
     guarded
    -0.62
     analog
    -0.61
    POSITIVE LOGITS
    Please
    3.33
    please
    2.32
     Please
    2.18
     PLEASE
    1.87
    Thank
    1.65
    Sorry
    1.63
     please
    1.56
    Feel
    1.44
    PLE
    1.38
    Dear
    1.32
    Activations Density 0.019%

    No Known Activations