© 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. 12274
    Prev
    Next
    INDEX
    Explanations

    instances of characters or places frequently mentioned or significant in context

    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
    0:0.07
    1:0.02
    2:0.03
    3:0.05
    4:0.06
    5:0.05
    6:0.15
    7:0.04
    8:0.18
    9:0.24
    10:0.03
    11:0.03
    Negative Logits
     Pascal
    -4.14
     glim
    -3.89
    ヴ
    -3.66
     Faust
    -3.58
     −
    -3.58
     Sweeney
    -3.54
     sink
    -3.50
     Huang
    -3.44
    −
    -3.38
    Gil
    -3.37
    POSITIVE LOGITS
    Kansas
    9.46
     Kansas
    9.24
     Chiefs
    8.51
     KC
    7.48
     KS
    6.41
    KC
    6.31
     Royals
    5.41
    KS
    5.19
    AK
    5.03
     Wichita
    4.98
    Activations Density 0.005%

    No Known Activations