© 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. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 16279
    Prev
    Next
    INDEX
    Explanations

    elements of humor and reactions to social comedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.03
    2:0.13
    3:0.05
    4:0.05
    5:0.05
    6:0.18
    7:0.04
    8:0.03
    9:0.24
    10:0.03
    11:0.02
    Negative Logits
     RAID
    -3.59
     Sovere
    -3.43
     Shards
    -3.42
    Catal
    -3.36
    aiden
    -3.31
     Awoken
    -3.22
    Raid
    -3.21
     Sek
    -3.12
     Blades
    -3.11
     Catalyst
    -3.11
    POSITIVE LOGITS
     humor
    7.07
     laughter
    6.88
     jokes
    6.84
     comedy
    6.73
     laugh
    6.68
     laughing
    6.58
     joke
    6.51
     comedians
    6.34
     Comedy
    6.24
     comedic
    6.20
    Activations Density 0.022%

    No Known Activations