© 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 EvalsExportsinterp-engineNEWAPI 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. 9262
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to wit or cleverness

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "wit" and its variations, emphasizing cleverness 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
     enrollment
    -0.74
     obligated
    -0.72
     tradem
    -0.68
     mosqu
    -0.67
     surve
    -0.65
     predatory
    -0.63
     tracked
    -0.63
     servicing
    -0.62
     fracturing
    -0.61
     absentee
    -0.61
    POSITIVE LOGITS
    hered
    1.51
    chery
    1.21
    glers
    1.11
    combe
    0.97
    ener
    0.92
    cher
    0.90
    nesses
    0.87
    bill
    0.86
    herer
    0.86
    ician
    0.85
    Activations Density 0.016%

    No Known Activations