© 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. 17752
    Prev
    Next
    INDEX
    Explanations

    forms of wordplay, particularly puns

    oai_token-act-pair · gpt-3.5-turbo

    instances of wordplay focused on puns

    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
     Consent
    -0.71
     Empires
    -0.70
     Commons
    -0.69
    STD
    -0.65
     Biological
    -0.65
     Journals
    -0.64
     Refuge
    -0.63
     Issues
    -0.61
     Coh
    -0.61
     Divinity
    -0.61
    POSITIVE LOGITS
    isher
    1.08
    ishers
    1.04
    pun
    1.03
     pun
    1.00
    cheon
    0.93
    itive
    0.90
    ting
    0.86
    oons
    0.85
    itial
    0.84
    hett
    0.82
    Activations Density 0.005%

    No Known Activations