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. 9-ATT-KK
    6. 7729
    Prev
    Next
    INDEX
    Explanations

    terms related to maritime activities and incidents

    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
    0:0.12
    1:0.01
    2:0.10
    3:0.09
    4:0.02
    5:0.08
    6:0.04
    7:0.04
    8:0.38
    9:0.02
    10:0.02
    11:0.02
    Negative Logits
     CPS
    -3.69
    Denver
    -3.63
    �
    -3.15
    Chicago
    -3.15
    ş
    -2.86
     Nuggets
    -2.85
    Detroit
    -2.83
    Miller
    -2.81
    Urban
    -2.80
     Scha
    -2.79
    POSITIVE LOGITS
     ashore
    7.20
     seaw
    6.43
     reefs
    6.40
     sailors
    6.35
     sail
    6.21
     seaf
    6.10
     sailing
    6.09
     sailor
    6.06
     coral
    5.94
     reef
    5.88
    Activations Density 0.747%

    No Known Activations