© 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. 6917
    Prev
    Next
    INDEX
    Explanations

    statements related to polling and public opinion data

    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
    0:0.13
    1:0.04
    2:0.10
    3:0.05
    4:0.05
    5:0.08
    6:0.11
    7:0.07
    8:0.09
    9:0.16
    10:0.04
    11:0.03
    Negative Logits
     Blades
    -3.81
     Nek
    -3.47
     Tek
    -3.43
    Tes
    -3.38
     Nig
    -3.33
     blade
    -3.32
     swaps
    -3.30
    Wan
    -3.27
     Duc
    -3.17
     ASIC
    -3.17
    POSITIVE LOGITS
     Gallup
    7.95
    Gall
    5.54
    Americans
    3.56
     Hoover
    3.48
     polling
    3.32
     polled
    3.31
     Poll
    3.23
    ████████
    3.22
    Pers
    3.17
    ÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂÃÂ
    3.17
    Activations Density 0.002%

    No Known Activations