© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 516
    Prev
    Next
    INDEX
    Explanations

    instances of affirmation or certainty in statements

    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
    0:0.09
    1:0.03
    2:0.10
    3:0.04
    4:0.05
    5:0.05
    6:0.18
    7:0.05
    8:0.10
    9:0.18
    10:0.03
    11:0.04
    Negative Logits
    三
    -3.95
     Samoa
    -3.87
     samurai
    -3.69
     Zoro
    -3.64
     fam
    -3.63
    obyl
    -3.63
    ゴン
    -3.55
    Alias
    -3.49
    ahime
    -3.43
     villagers
    -3.40
    POSITIVE LOGITS
     Steele
    10.94
    Ste
    6.48
    eele
    5.51
     Stein
    4.67
     Stone
    4.30
     Fusion
    3.98
     Transfer
    3.97
     Ste
    3.90
     Stef
    3.88
     Stellar
    3.86
    Activations Density 0.001%

    No Known Activations