© 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. 10-ATT-KK
    11. 8682
    Prev
    Next
    INDEX
    Explanations

    numerical data and percentages related to polling results

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.07
    2:0.10
    3:0.06
    4:0.11
    5:0.08
    6:0.10
    7:0.07
    8:0.06
    9:0.10
    10:0.04
    11:0.12
    Negative Logits
     subpoena
    -2.41
     Cosmetic
    -2.33
     Complex
    -2.33
     Recipes
    -2.30
    acre
    -2.24
    doc
    -2.18
     Beautiful
    -2.18
    wordpress
    -2.17
     subpoen
    -2.16
     Lol
    -2.15
    POSITIVE LOGITS
     polled
    3.86
     polling
    3.59
    poll
    3.49
     polls
    3.23
    Romney
    3.18
     poll
    3.15
     margins
    3.10
     averages
    3.10
    espie
    3.04
     trailed
    2.99
    Activations Density 0.077%

    No Known Activations