Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 16090
    Prev
    Next
    INDEX
    Explanations

    words related to laughter or amusement

    oai_token-act-pair · gpt-3.5-turbo

    instances of laughter or expressions of humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pled
    -0.74
    tnc
    -0.63
    inence
    -0.62
     Skydragon
    -0.59
     administrative
    -0.59
     confir
    -0.58
    interstitial
    -0.58
    accompan
    -0.57
     chall
    -0.57
     newsletters
    -0.56
    POSITIVE LOGITS
     hyster
    1.25
    ably
    1.11
     uproar
    1.11
     maniac
    1.09
     aloud
    1.03
    stocks
    0.95
     uncontroll
    0.94
     nervously
    0.93
    ingly
    0.90
     loudly
    0.81
    Activations Density 0.047%

    No Known Activations