© 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. 23653
    Prev
    Next
    INDEX
    Explanations

    references to controversial or satirical cartoons, particularly those that engage with political or social issues

    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
    0:0.30
    1:0.02
    2:0.08
    3:0.08
    4:0.03
    5:0.06
    6:0.08
    7:0.05
    8:0.09
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
     Records
    -3.06
     sealing
    -2.99
    ighthouse
    -2.61
     registry
    -2.59
     Registry
    -2.56
    etooth
    -2.55
     clinch
    -2.50
     Reach
    -2.50
    ntil
    -2.42
     Payments
    -2.41
    POSITIVE LOGITS
     cartoons
    8.16
     cartoon
    7.76
     Cartoon
    7.25
     animated
    4.83
     caric
    4.81
    Cart
    4.71
     comics
    4.69
     anim
    4.48
     animation
    4.46
    Animation
    4.38
    Activations Density 0.025%

    No Known Activations