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. 6-RES-JB
    6. 10540
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences related to laughter or amusement

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to making fun of situations or people

    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
    isSpecialOrderable
    -0.88
    awei
    -0.87
     defic
    -0.85
    soDeliveryDate
    -0.83
     dilig
    -0.83
    priority
    -0.81
     permissions
    -0.77
     priority
    -0.74
     metab
    -0.72
    avering
    -0.72
    POSITIVE LOGITS
     jokes
    1.16
     joke
    0.92
     trivia
    0.89
     banter
    0.87
     Barney
    0.86
     laughs
    0.81
     Goldberg
    0.81
     joking
    0.81
     gigg
    0.81
     Stupid
    0.80
    Activations Density 0.282%

    No Known Activations