© 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. 13784
    Prev
    Next
    INDEX
    Explanations

    phrases indicating potential or possibility

    oai_token-act-pair · gpt-3.5-turbo

    the word "could" indicating potential or possibility

    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
     Mondays
    -0.57
     Everyday
    -0.51
    phies
    -0.50
     accordance
    -0.50
    arters
    -0.48
     BCC
    -0.48
    arter
    -0.48
     majority
    -0.47
     Fridays
    -0.47
    faith
    -0.47
    POSITIVE LOGITS
     could
    2.95
    could
    2.64
     Could
    2.04
     couldn
    1.88
    Could
    1.86
     would
    1.72
     might
    1.69
     wouldn
    1.66
    OULD
    1.62
    would
    1.58
    Activations Density 0.091%

    No Known Activations