© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 17849
    Prev
    Next
    INDEX
    Explanations

    phrases related to humor or something not to be taken seriously

    oai_token-act-pair · gpt-3.5-turbo

    references to jokes or humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    undai
    -0.87
    phalt
    -0.77
    ignt
    -0.71
    ignty
    -0.71
    enture
    -0.69
    orneys
    -0.68
    rity
    -0.66
    porting
    -0.66
    arnaev
    -0.66
    CLASSIFIED
    -0.66
    POSITIVE LOGITS
    ously
    1.04
     jokes
    0.87
     mocking
    0.84
     joke
    0.81
    fest
    0.78
     joking
    0.78
    osal
    0.78
    bags
    0.77
    bag
    0.76
     Pom
    0.76
    Activations Density 0.026%

    No Known Activations