© 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. 9-ATT-KK
    11. 8746
    Prev
    Next
    INDEX
    Explanations

    references to skyscrapers or tall buildings

    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
    0:0.22
    1:0.02
    2:0.24
    3:0.08
    4:0.03
    5:0.09
    6:0.05
    7:0.04
    8:0.09
    9:0.04
    10:0.03
    11:0.02
    Negative Logits
     abstinence
    -3.35
     inoc
    -3.03
     Volunte
    -3.00
     Rebell
    -2.89
     vacc
    -2.82
     volunt
    -2.72
     Volunteers
    -2.70
     Infect
    -2.68
     volunteering
    -2.67
     antibiotics
    -2.66
    POSITIVE LOGITS
     towers
    5.38
     tower
    4.97
     skysc
    4.96
     Towers
    4.94
     tallest
    4.85
     taller
    4.54
     Tower
    4.38
     height
    3.87
    tower
    3.82
    hattan
    3.80
    Activations Density 0.031%

    No Known Activations