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

    Neuronpedia

    APICircuit 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. 4-RES-JB
    6. 19208
    Prev
    Next
    INDEX
    Explanations

    phrases related to jokes or humorous content

    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 @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    porting
    -0.72
    undai
    -0.71
    phalt
    -0.71
    ignt
    -0.70
    aining
    -0.69
    actions
    -0.68
    orneys
    -0.68
    rates
    -0.68
    ighting
    -0.67
    enture
    -0.67
    POSITIVE LOGITS
    ously
    1.01
     jokes
    0.91
     joke
    0.89
     banter
    0.83
     joking
    0.83
    itone
    0.78
    bags
    0.77
     mocking
    0.76
     Pom
    0.75
    osal
    0.74
    Activations Density 0.014%

    No Known Activations