© 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. 10-ATT-KK
    11. 8029
    Prev
    Next
    INDEX
    Explanations

    keywords related to political entities and events

    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
    1:0.02
    2:0.02
    3:0.03
    4:0.03
    5:0.03
    6:0.04
    7:0.06
    8:0.02
    9:0.23
    10:0.02
    11:0.41
    Negative Logits
     visitation
    -2.35
     daylight
    -2.09
    opia
    -1.99
    endum
    -1.96
     unity
    -1.92
     adolescence
    -1.91
    eur
    -1.89
    lement
    -1.89
     goodwill
    -1.85
    iment
    -1.84
    POSITIVE LOGITS
     destinations
    2.88
     contenders
    2.78
    TOP
    2.68
    lists
    2.67
     rankings
    2.61
     spots
    2.52
     positions
    2.52
     ranking
    2.48
     list
    2.47
     lists
    2.42
    Activations Density 0.056%

    No Known Activations