© 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. 10-RES-JB
    11. 24461
    Prev
    Next
    INDEX
    Explanations

    instances of irony or paradoxes in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to irony and paradox

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ENG
    -0.68
     controllers
    -0.67
    Storage
    -0.67
    GET
    -0.65
    unte
    -0.64
    lee
    -0.64
    EVA
    -0.64
    Crash
    -0.62
    artney
    -0.62
    Interstitial
    -0.62
    POSITIVE LOGITS
     juxtap
    1.02
     irony
    0.91
     paradox
    0.86
     twist
    0.81
     parallels
    0.80
     mockery
    0.79
     Osw
    0.78
    bringer
    0.77
     ironic
    0.74
     inherent
    0.74
    Activations Density 0.078%

    No Known Activations