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. 3041
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the word "as" and variations of the verb "to be"

    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
    0:0.03
    1:0.02
    2:0.05
    3:0.06
    4:0.05
    5:0.04
    6:0.39
    7:0.04
    8:0.06
    9:0.08
    10:0.07
    11:0.05
    Negative Logits
     innocence
    -1.39
     blackout
    -1.34
     remission
    -1.22
     landfall
    -1.21
     hover
    -1.20
     Haram
    -1.20
     breastfeeding
    -1.19
     dehydration
    -1.18
     tampering
    -1.18
     payment
    -1.17
    POSITIVE LOGITS
    anium
    1.98
    ️
    1.68
    actionDate
    1.62
    inki
    1.56
    iverse
    1.51
    rison
    1.50
    emark
    1.49
    ゼ
    1.41
    initialized
    1.41
    enhagen
    1.36
    Activations Density 0.010%

    No Known Activations