© 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. 1-RES-JB
    11. 24145
    Prev
    Next
    INDEX
    Explanations

    parodies and satirical content in text

    oai_token-act-pair · gpt-3.5-turbo

    instances of parody and satire in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erto
    -0.78
    oard
    -0.75
    Streamer
    -0.75
     violet
    -0.75
    vals
    -0.72
    negie
    -0.72
    rain
    -0.71
    Va
    -0.71
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.70
    Transfer
    -0.70
    POSITIVE LOGITS
     satir
    1.25
     satire
    1.25
     spoof
    1.21
     parody
    1.20
     mockery
    1.04
     mocking
    1.04
     satirical
    1.02
     caric
    1.00
     caricature
    0.91
    netflix
    0.88
    Activations Density 0.015%

    No Known Activations