© 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. 10-RES-JB
    11. 7741
    Prev
    Next
    INDEX
    Explanations

    instances of phrases related to teasing or making fun of someone or something

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to humor and playful critiques

    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
    Interstitial
    -0.76
    Decl
    -0.74
    ript
    -0.73
    Loading
    -0.72
    ifted
    -0.71
    ife
    -0.68
    oppable
    -0.67
    Quantity
    -0.64
    Aid
    -0.64
    ufact
    -0.63
    POSITIVE LOGITS
     holes
    1.12
     fun
    0.99
     wink
    0.91
     peek
    0.86
     quizz
    0.86
     poking
    0.84
     poke
    0.83
     teasing
    0.80
     glimps
    0.79
     hole
    0.78
    Activations Density 0.090%

    No Known Activations