© 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. 14959
    Prev
    Next
    INDEX
    Explanations

    medical and health-related associations involving participants

    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
    0:0.08
    1:0.05
    2:0.08
    3:0.12
    4:0.12
    5:0.05
    6:0.10
    7:0.07
    8:0.05
    9:0.06
    10:0.06
    11:0.11
    Negative Logits
     daddy
    -2.84
     Daddy
    -2.44
    Oracle
    -2.41
     Klingon
    -2.41
    udicrous
    -2.34
     Luffy
    -2.22
     Bentley
    -2.21
    gob
    -2.21
     Founders
    -2.20
     Deals
    -2.19
    POSITIVE LOGITS
     cohort
    3.90
     questionnaire
    3.77
     outpatient
    3.58
     mortality
    3.50
     ≥
    3.42
     patients
    3.38
     Patients
    3.35
     placebo
    3.23
     responders
    3.22
     cohorts
    3.20
    Activations Density 0.120%

    No Known Activations