© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15756
    Prev
    Next
    INDEX
    Explanations

    useful Muay Thai combo techniques and their descriptions

    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
    0:0.16
    1:0.09
    2:0.09
    3:0.07
    4:0.07
    5:0.03
    6:0.12
    7:0.09
    8:0.02
    9:0.04
    10:0.09
    11:0.08
    Negative Logits
     Pip
    -3.14
     Bild
    -3.08
     Dahl
    -2.97
     Tuc
    -2.88
     Darling
    -2.86
     Stafford
    -2.69
     Eisenhower
    -2.65
     Vienna
    -2.64
    RH
    -2.63
     Pigs
    -2.62
    POSITIVE LOGITS
     combos
    5.64
     combo
    5.57
     Combo
    5.17
     Brawl
    3.43
     Mew
    3.42
     KO
    3.36
     reset
    3.35
     meter
    3.27
     Chun
    2.98
     spacing
    2.97
    Activations Density 0.004%

    No Known Activations