© 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 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. 13693
    Prev
    Next
    INDEX
    Explanations

    phrases related to player performance and skills in hockey

    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
    1:0.01
    2:0.10
    3:0.08
    4:0.02
    5:0.04
    6:0.04
    7:0.03
    8:0.51
    9:0.02
    10:0.02
    11:0.01
    Negative Logits
     plantation
    -3.83
     evangelical
    -3.67
     Zimbabwe
    -3.65
     Liberia
    -3.64
     Osiris
    -3.59
     Nile
    -3.59
     pastors
    -3.58
    African
    -3.55
     Exodus
    -3.48
    Bey
    -3.45
    POSITIVE LOGITS
     NHL
    7.55
     hockey
    7.52
     puck
    7.49
     Hockey
    7.21
     rink
    7.02
     skating
    6.86
     goaltender
    6.82
     defenseman
    6.75
     Canucks
    6.69
     goalie
    6.53
    Activations Density 0.707%

    No Known Activations