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. 14646
    Prev
    Next
    INDEX
    Explanations

    references to religious themes and censorship issues

    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
    2:0.04
    3:0.09
    4:0.08
    5:0.02
    6:0.10
    7:0.11
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
     Bowser
    -3.76
    ovych
    -3.57
     Snake
    -3.41
     Sounders
    -3.39
    Seattle
    -3.30
    Snake
    -3.23
     Mario
    -3.22
     streetcar
    -3.20
     Leafs
    -3.02
    Mario
    -2.99
    POSITIVE LOGITS
     blasphemy
    8.14
     blasp
    6.79
    hemy
    5.04
     clerics
    4.44
     lyn
    4.41
    Pakistan
    4.28
     Koran
    4.23
     Quran
    4.09
    Muslims
    4.06
     Prophet
    4.06
    Activations Density 0.002%

    No Known Activations