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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 5-ATT-KK
    6. 3038
    Prev
    Next
    INDEX
    Explanations

    phrases that express the concept of giving someone the benefit of the doubt

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.10
    3:0.06
    4:0.08
    5:0.02
    6:0.28
    7:0.22
    8:0.03
    9:0.03
    10:0.04
    11:0.05
    Negative Logits
    soDeliveryDate
    -1.74
    ugu
    -1.52
    urnal
    -1.50
    igmat
    -1.48
     Archdemon
    -1.47
    の魔
    -1.46
    �
    -1.41
    yout
    -1.41
    quartered
    -1.40
    thro
    -1.35
    POSITIVE LOGITS
     export
    1.41
     Immunity
    1.32
     punches
    1.29
     Export
    1.25
     Trading
    1.24
     improv
    1.24
     trade
    1.22
     persuasion
    1.22
     ridicule
    1.21
     conferred
    1.20
    Activations Density 0.001%

    No Known Activations