© 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. 11-RES-JB
    11. 2652
    Prev
    Next
    INDEX
    Explanations

    critiquing or discussing comedy and jokes

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the consequences of dark humor and societal perceptions of comedy

    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
    20439
    -0.84
     Sovere
    -0.81
    spec
    -0.79
     Pwr
    -0.78
     sealing
    -0.78
    izu
    -0.76
    RNA
    -0.76
    rolet
    -0.76
     Priority
    -0.76
    venants
    -0.75
    POSITIVE LOGITS
     jokes
    2.05
     humor
    2.02
     humorous
    1.92
     humour
    1.92
     joke
    1.89
     laughs
    1.89
     satire
    1.88
     laughter
    1.86
     laugh
    1.85
     satir
    1.83
    Activations Density 0.638%

    No Known Activations