© 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. 4-RES-JB
    11. 10092
    Prev
    Next
    INDEX
    Explanations

    words related to humor or comedic elements

    oai_token-act-pair · gpt-3.5-turbo

    references to humor and comedic elements

    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
    holder
    -0.68
    arnaev
    -0.67
    FT
    -0.62
    Ag
    -0.60
    minster
    -0.59
     Peaks
    -0.58
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    -0.57
     opio
    -0.57
     eyed
    -0.57
    REAM
    -0.57
    POSITIVE LOGITS
    ously
    1.29
     humour
    0.95
     humor
    0.94
    ably
    0.91
    ingly
    0.81
    lessly
    0.81
    netflix
    0.80
    isma
    0.76
    atur
    0.76
    osity
    0.75
    Activations Density 0.017%

    No Known Activations