© 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. 13630
    Prev
    Next
    INDEX
    Explanations

    the word "enjoying" in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "enjoying" and related terms that express the feeling of enjoyment

    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
    DN
    -0.73
     precursor
    -0.72
     false
    -0.70
     Cosponsors
    -0.69
    letter
    -0.68
    ask
    -0.67
     letter
    -0.67
     Deter
    -0.66
    letters
    -0.64
    Letter
    -0.64
    POSITIVE LOGITS
     enjoying
    3.35
     enjoyment
    1.74
     enjoys
    1.45
     enjoyed
    1.42
     celebrating
    1.40
     enjoy
    1.38
     Enjoy
    1.35
    Enjoy
    1.34
     liking
    1.33
     grinning
    1.31
    Activations Density 0.021%

    No Known Activations