© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43540
    Prev
    Next
    INDEX
    Explanations

    expressions of humor and irony

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.05
    3:0.08
    4:0.12
    5:0.02
    6:0.04
    7:0.40
    8:0.03
    9:0.03
    10:0.05
    11:0.08
    Negative Logits
    ailability
    -2.33
     tradem
    -2.04
    phabet
    -1.97
    apons
    -1.91
    psey
    -1.84
    querque
    -1.74
    ngth
    -1.72
    ompl
    -1.69
    chnology
    -1.68
    ascus
    -1.67
    POSITIVE LOGITS
     Lange
    1.61
     [&
    1.59
     jokes
    1.57
    Planet
    1.50
     Watkins
    1.46
     Doodle
    1.38
     McA
    1.37
     Unch
    1.36
     Simple
    1.33
     Constable
    1.33
    Activations Density 0.006%

    No Known Activations