© 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. 8361
    Prev
    Next
    INDEX
    Explanations

    questions related to political commentary and media discussions

    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
    0:0.17
    1:0.12
    2:0.06
    3:0.07
    4:0.05
    5:0.03
    6:0.12
    7:0.13
    8:0.02
    9:0.05
    10:0.09
    11:0.05
    Negative Logits
     plantations
    -2.88
     Jakarta
    -2.62
     Eclipse
    -2.55
    aido
    -2.52
    sterdam
    -2.51
    Zen
    -2.50
    ikk
    -2.49
     Ruler
    -2.39
     Tak
    -2.38
     Alonso
    -2.35
    POSITIVE LOGITS
     Fallon
    7.10
    Fall
    4.17
     Benghazi
    3.53
     Vault
    2.76
    Secretary
    2.76
     Gow
    2.72
    ghazi
    2.70
     Colbert
    2.70
     HBO
    2.69
     Bravo
    2.68
    Activations Density 0.005%

    No Known Activations