© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 445
    Prev
    Next
    INDEX
    Explanations

    occurrences of political or legal terms

    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
    0:0.05
    1:0.36
    2:0.04
    3:0.05
    4:0.04
    5:0.04
    6:0.13
    7:0.04
    8:0.04
    9:0.09
    10:0.03
    11:0.03
    Negative Logits
     fifty
    -3.17
     forty
    -2.98
     sixty
    -2.93
     thirty
    -2.78
    itely
    -2.72
    ivably
    -2.72
    510
    -2.56
     twenty
    -2.56
    acebook
    -2.52
    536
    -2.52
    POSITIVE LOGITS
     main
    5.33
    main
    5.33
     Main
    4.36
    Main
    4.24
     mainly
    3.80
    mostly
    3.41
     mostly
    3.19
     Mostly
    2.96
     biggest
    2.81
     major
    2.64
    Activations Density 0.002%

    No Known Activations