© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 2-RES-JB
    11. 12879
    Prev
    Next
    INDEX
    Explanations

    words related to irony

    oai_token-act-pair · gpt-3.5-turbo

    expressions of irony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eding
    -0.87
    erto
    -0.81
    hani
    -0.77
    Interstitial
    -0.75
    á
    -0.75
    lished
    -0.75
    tests
    -0.75
    league
    -0.75
    eder
    -0.74
    undy
    -0.73
    POSITIVE LOGITS
     irony
    1.09
     ironic
    1.03
     twist
    0.93
     wink
    0.81
     reversal
    0.81
     sidel
    0.81
     paradox
    0.80
     ironically
    0.78
     juxtap
    0.76
     Osw
    0.71
    Activations Density 0.013%

    No Known Activations