© 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. 14088
    Prev
    Next
    INDEX
    Explanations

    terms related to sports teams and their defensive performance

    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
    0:0.05
    1:0.02
    2:0.09
    3:0.04
    4:0.04
    5:0.04
    6:0.24
    7:0.03
    8:0.05
    9:0.28
    10:0.02
    11:0.03
    Negative Logits
     tou
    -3.86
    Charl
    -3.85
    Thom
    -3.83
     Pumpkin
    -3.74
     Notting
    -3.72
     Hyde
    -3.70
     plush
    -3.58
     Thom
    -3.56
     Lotus
    -3.55
     Ou
    -3.55
    POSITIVE LOGITS
    Defense
    7.94
     Defense
    7.89
     DEFENSE
    7.45
     defense
    7.30
    defense
    7.10
     Defence
    6.66
     defenses
    6.20
     defence
    5.50
    DEF
    5.34
     Defensive
    5.20
    Activations Density 0.016%

    No Known Activations