Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11130
    Prev
    Next
    INDEX
    Explanations

    phrases related to hockey performance and player evaluations

    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
    1:0.03
    2:0.08
    3:0.15
    4:0.04
    5:0.08
    6:0.04
    7:0.07
    8:0.24
    9:0.04
    10:0.06
    11:0.04
    Negative Logits
     Ethiop
    -3.56
     Birmingham
    -3.53
     Ethiopian
    -3.25
     Ethiopia
    -3.22
     Osiris
    -3.17
     Alabama
    -3.17
     Ala
    -3.10
     Racial
    -2.97
     Saban
    -2.96
    Alabama
    -2.96
    POSITIVE LOGITS
     puck
    5.38
     skating
    3.83
     defenseman
    3.83
    ipeg
    3.81
     hockey
    3.77
     rink
    3.60
     ice
    3.49
     Malk
    3.44
     linem
    3.40
     skate
    3.38
    Activations Density 0.014%

    No Known Activations