Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 3140
    Prev
    Next
    INDEX
    Explanations

    references to hospitals and related institutions

    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
    0:0.10
    1:0.03
    2:0.07
    3:0.08
    4:0.05
    5:0.08
    6:0.05
    7:0.07
    8:0.26
    9:0.06
    10:0.05
    11:0.04
    Negative Logits
     Sicily
    -3.81
     Naples
    -3.79
     Giul
    -3.36
     Italians
    -3.26
     Serie
    -3.25
     Florence
    -3.10
     Greeks
    -3.07
    osta
    -3.02
     Italian
    -3.02
     Constantine
    -2.96
    POSITIVE LOGITS
    igham
    3.01
     Brigham
    2.77
     Xu
    2.70
    Hong
    2.68
     Bain
    2.58
    JD
    2.55
     Cambod
    2.54
     Guan
    2.54
     JD
    2.52
     NCT
    2.52
    Activations Density 0.000%

    No Known Activations