© 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. 0-RES-JB
    11. 9824
    Prev
    Next
    INDEX
    Explanations

    instances where the word "may" is used in a sentence indicating a possibility or permission

    oai_token-act-pair · gpt-3.5-turbo

    the word "may" and its variations to indicate possibility or uncertainty

    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
    clusively
    -0.64
    UTC
    -0.61
     EVER
    -0.59
    ordable
    -0.59
    geries
    -0.57
    aza
    -0.57
    everything
    -0.55
    udding
    -0.53
    atts
    -0.53
    english
    -0.52
    POSITIVE LOGITS
     may
    2.95
     might
    2.19
    may
    2.07
    might
    1.89
     MAY
    1.88
     could
    1.51
     cannot
    1.51
     shall
    1.42
     must
    1.42
     can
    1.40
    Activations Density 0.054%

    No Known Activations