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. 14568
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal agreements and community service requirements

    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
    0:0.14
    1:0.19
    2:0.07
    3:0.05
    4:0.03
    5:0.01
    6:0.06
    7:0.11
    8:0.02
    9:0.03
    10:0.20
    11:0.04
    Negative Logits
     Ys
    -2.92
    Ware
    -2.89
     Xin
    -2.85
    redo
    -2.83
    Blade
    -2.81
    warts
    -2.77
    Edge
    -2.69
    Í
    -2.62
    xia
    -2.58
     Carbuncle
    -2.57
    POSITIVE LOGITS
     Hum
    8.63
    Hum
    6.12
    hum
    5.98
     hum
    5.49
     HUM
    5.35
     humming
    3.63
     humid
    3.61
     Hib
    3.52
     Nam
    3.47
     Hos
    3.31
    Activations Density 0.004%

    No Known Activations