© 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. 0-RES-JB
    11. 4198
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to laughter

    oai_token-act-pair · gpt-3.5-turbo

    instances of people laughing and associated playful expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Order
    -0.73
    order
    -0.68
    vernment
    -0.67
    inances
    -0.66
    yssey
    -0.66
    ought
    -0.65
    Forge
    -0.64
    Direct
    -0.64
     UE
    -0.63
    Availability
    -0.63
    POSITIVE LOGITS
     laughing
    3.85
     smiling
    2.16
     laughter
    2.10
     grinning
    2.05
     joking
    1.85
     gigg
    1.83
    laugh
    1.79
     crying
    1.77
     weeping
    1.74
     laugh
    1.70
    Activations Density 0.014%

    No Known Activations