© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3586
    Prev
    Next
    INDEX
    Explanations

    terms related to rankings and physical attributes of players

    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
    1:0.04
    2:0.08
    3:0.04
    4:0.04
    5:0.04
    6:0.21
    7:0.04
    8:0.07
    9:0.23
    10:0.03
    11:0.04
    Negative Logits
     Swim
    -4.13
     Indra
    -3.90
    aila
    -3.85
    Na
    -3.83
     Na
    -3.77
     Hansen
    -3.62
    aina
    -3.47
    ima
    -3.46
    š
    -3.41
    eva
    -3.38
    POSITIVE LOGITS
     corner
    7.39
     Corner
    7.21
     corners
    6.80
    cor
    4.42
    Cor
    4.41
     cornerback
    4.30
     Chester
    3.49
     Chev
    3.49
     Cor
    3.47
     wedge
    3.46
    Activations Density 0.002%

    No Known Activations