© 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. 12409
    Prev
    Next
    INDEX
    Explanations

    questions and statements that relate to expectations or perceptions of medical treatments and their effects

    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
    0:0.04
    1:0.01
    2:0.06
    3:0.10
    4:0.09
    5:0.10
    6:0.04
    7:0.11
    8:0.28
    9:0.02
    10:0.04
    11:0.05
    Negative Logits
    Sham
    -3.42
     Korra
    -3.27
     Yen
    -3.16
     Yak
    -3.08
     Taiwanese
    -3.07
     Taiwan
    -3.02
    HK
    -3.01
     Kok
    -3.00
     Helsinki
    -2.98
     Finland
    -2.97
    POSITIVE LOGITS
     Lucius
    3.81
    anus
    3.34
    orem
    3.28
    ibus
    3.22
     membr
    3.19
    iatus
    3.15
     Corpus
    3.06
     Cato
    2.98
     corpus
    2.93
     nutrit
    2.90
    Activations Density 0.024%

    No Known Activations