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. 14589
    Prev
    Next
    INDEX
    Explanations

    evidence and mentions surrounding authority figures and their actions

    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
    0:0.23
    1:0.06
    2:0.09
    3:0.05
    4:0.03
    5:0.02
    6:0.11
    7:0.10
    8:0.02
    9:0.04
    10:0.14
    11:0.04
    Negative Logits
     Jac
    -3.45
    76561
    -3.42
    �
    -3.21
     Lucia
    -3.17
     Tau
    -3.17
     Fal
    -3.10
     DJs
    -3.07
     Alv
    -3.07
     Drone
    -2.99
     CCP
    -2.89
    POSITIVE LOGITS
     Snyder
    10.11
    nyder
    7.37
     Flint
    5.63
    Michigan
    4.68
     Luthor
    4.56
     Lansing
    4.46
     Michigan
    4.45
     Detroit
    4.29
    Detroit
    4.13
     Spartans
    3.95
    Activations Density 0.012%

    No Known Activations