© 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. 9-ATT-KK
    11. 14866
    Prev
    Next
    INDEX
    Explanations

    references to the "Blues" in various contexts, as well as the dynamics of team performance and player negotiations

    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
    0:0.10
    1:0.03
    2:0.06
    3:0.05
    4:0.04
    5:0.04
    6:0.09
    7:0.05
    8:0.36
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
     Erdogan
    -4.48
    ğ
    -4.16
     Ankara
    -3.96
     Istanbul
    -3.88
    Turkey
    -3.76
    ş
    -3.74
    ı
    -3.72
    oğ
    -3.71
    oglu
    -3.54
     Turkey
    -3.42
    POSITIVE LOGITS
     Blues
    7.37
     blues
    5.47
    etsk
    3.66
     Willie
    3.50
     Norfolk
    3.44
     Negro
    3.16
     Roberts
    3.14
     Skinner
    3.09
     Hitchcock
    3.05
     aft
    3.02
    Activations Density 0.002%

    No Known Activations