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. 229
    Prev
    Next
    INDEX
    Explanations

    terms related to football players and their actions in the game

    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
    0:0.12
    1:0.03
    2:0.07
    3:0.05
    4:0.04
    5:0.06
    6:0.18
    7:0.06
    8:0.20
    9:0.10
    10:0.03
    11:0.03
    Negative Logits
    enhagen
    -4.06
     Uganda
    -3.96
     Copenhagen
    -3.84
    deen
    -3.74
    ø
    -3.68
    aber
    -3.67
     Rubio
    -3.62
     Peak
    -3.48
     Rwanda
    -3.45
     Denmark
    -3.43
    POSITIVE LOGITS
     Colts
    9.68
     Indianapolis
    7.50
     Indy
    6.52
    Indian
    5.81
     Luck
    5.77
     Colt
    5.59
     RG
    4.51
     Peyton
    4.50
    Luck
    4.44
     AFC
    4.37
    Activations Density 0.005%

    No Known Activations