© 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. 9-RES-JB
    11. 17451
    Prev
    Next
    INDEX
    Explanations

    instances of jokes or sarcastic comments

    oai_token-act-pair · gpt-3.5-turbo

    instances of humor or joking in contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¯
    -0.69
    arrow
    -0.69
    ãĥĩ
    -0.69
    photo
    -0.67
    ãĥ¼ãĥ«
    -0.66
    FL
    -0.62
     Liberties
    -0.62
    href
    -0.61
    available
    -0.61
    keys
    -0.61
    POSITIVE LOGITS
     aloud
    1.25
     nostalg
    1.07
     bitterly
    1.06
     sarcast
    1.04
     confidently
    1.04
     loudly
    1.03
     about
    1.00
     passionately
    0.98
     omin
    0.96
     approving
    0.91
    Activations Density 0.116%

    No Known Activations