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. 14667
    Prev
    Next
    INDEX
    Explanations

    references to creators or expressions of dissatisfaction regarding media productions

    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
    0:0.28
    1:0.05
    2:0.05
    3:0.05
    4:0.07
    5:0.02
    6:0.10
    7:0.09
    8:0.02
    9:0.04
    10:0.09
    11:0.07
    Negative Logits
    ovych
    -4.71
     Yanukovych
    -4.19
     Ukrain
    -3.80
     Dup
    -3.40
    henko
    -3.33
    ortmund
    -3.30
    oshenko
    -3.29
    vim
    -3.27
     Marse
    -3.24
     Sark
    -3.21
    POSITIVE LOGITS
     Morty
    7.48
    arlane
    5.14
     Cartoon
    4.25
     Toys
    4.24
     Gunn
    4.22
    Rick
    4.10
     Transformers
    3.80
     Adult
    3.80
     Spawn
    3.71
     Minecraft
    3.70
    Activations Density 0.003%

    No Known Activations