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. 5-ATT-KK
    6. 19238
    Prev
    Next
    INDEX
    Explanations

    phrases related to casualties and loss in various contexts

    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
    1:0.01
    2:0.07
    3:0.06
    4:0.10
    5:0.03
    6:0.03
    7:0.35
    8:0.04
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
    interpret
    -1.71
    aware
    -1.58
    Website
    -1.57
    agall
    -1.57
     answ
    -1.45
    ribed
    -1.44
    authorized
    -1.41
     branching
    -1.41
    quote
    -1.40
     freely
    -1.39
    POSITIVE LOGITS
     casualties
    1.87
     injuries
    1.65
     wounds
    1.58
     losses
    1.57
     DV
    1.52
     battles
    1.50
     Hunger
    1.48
     casualty
    1.48
     Haz
    1.45
     Hurricanes
    1.45
    Activations Density 0.001%

    No Known Activations