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. 138
    Prev
    Next
    INDEX
    Explanations

    plays and key statistics in sports narratives

    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
    0:0.06
    1:0.01
    2:0.05
    3:0.17
    4:0.04
    5:0.11
    6:0.02
    7:0.05
    8:0.35
    9:0.02
    10:0.06
    11:0.02
    Negative Logits
     manga
    -3.07
    henko
    -2.96
     Suzuki
    -2.91
     Sven
    -2.88
    aido
    -2.84
     Kuro
    -2.81
     Mats
    -2.79
     ATP
    -2.78
     pengu
    -2.71
     Anders
    -2.69
    POSITIVE LOGITS
     Texans
    4.14
     touchdown
    3.84
    Alabama
    3.81
     Bengals
    3.67
     punt
    3.65
     Bills
    3.59
     fumble
    3.57
    Virginia
    3.56
     Colts
    3.54
    Tenn
    3.54
    Activations Density 0.151%

    No Known Activations