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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 14513
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or contingencies in agreements and policies

    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
    0:0.17
    1:0.07
    2:0.04
    3:0.12
    4:0.04
    5:0.03
    6:0.06
    7:0.16
    8:0.01
    9:0.06
    10:0.16
    11:0.03
    Negative Logits
     Ish
    -3.25
     ak
    -2.87
     ki
    -2.85
     HT
    -2.82
    ć
    -2.81
    ichita
    -2.73
     Herrera
    -2.60
     Cairo
    -2.53
    anka
    -2.51
     VW
    -2.48
    POSITIVE LOGITS
     Newfoundland
    6.94
     Labrador
    5.26
    foundland
    4.99
     Halifax
    4.15
     Greenland
    4.09
     Moose
    3.99
     Scotia
    3.92
    rador
    3.82
     Manit
    3.71
     Islanders
    3.58
    Activations Density 0.001%

    No Known Activations