© 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. 15903
    Prev
    Next
    INDEX
    Explanations

    patterns related to business strategies and competitive contexts

    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
    0:0.13
    1:0.05
    2:0.05
    3:0.10
    4:0.04
    5:0.02
    6:0.17
    7:0.18
    8:0.02
    9:0.04
    10:0.08
    11:0.08
    Negative Logits
     Anchorage
    -3.45
     Swanson
    -3.03
     troopers
    -2.75
     Burlington
    -2.62
    Anim
    -2.59
     Barber
    -2.57
     Ranger
    -2.55
     ranger
    -2.52
     Honolulu
    -2.52
     Hanson
    -2.51
    POSITIVE LOGITS
     UEFA
    4.24
     Champions
    4.22
     Bundesliga
    4.03
     Liga
    3.73
     FIFA
    3.52
     Fifa
    3.46
     Europa
    3.44
    ça
    3.43
     Bayern
    3.37
     Serie
    3.34
    Activations Density 0.009%

    No Known Activations