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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 14433
    Prev
    Next
    INDEX
    Explanations

    phrases indicating disappointment or dissatisfaction

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.23
    1:0.06
    2:0.05
    3:0.04
    4:0.06
    5:0.03
    6:0.08
    7:0.09
    8:0.03
    9:0.04
    10:0.18
    11:0.06
    Negative Logits
     Suzuki
    -3.81
    ���
    -3.30
    itamin
    -3.06
     Izan
    -3.04
    imoto
    -2.99
     Osh
    -2.99
     Neh
    -2.98
     Haku
    -2.97
     autoimmune
    -2.95
     Sonia
    -2.95
    POSITIVE LOGITS
     cock
    7.93
     Cock
    7.88
    cock
    6.75
     dick
    4.11
     cum
    4.08
     balls
    3.87
     Fitz
    3.77
     Balls
    3.75
     cess
    3.56
     whore
    3.51
    Activations Density 0.005%

    No Known Activations