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. 9-ATT-KK
    6. 49
    Prev
    Next
    INDEX
    Explanations

    topics related to legal bans on face veils in various countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.07
    1:0.01
    2:0.09
    3:0.08
    4:0.02
    5:0.05
    6:0.04
    7:0.04
    8:0.48
    9:0.03
    10:0.02
    11:0.01
    Negative Logits
     Erie
    -3.38
    hattan
    -3.38
     Cerberus
    -3.37
     Rosenthal
    -3.37
    Denver
    -3.33
     Leafs
    -3.31
     Irving
    -3.27
    ottesville
    -3.14
     Angels
    -3.10
     Pats
    -3.03
    POSITIVE LOGITS
     Senegal
    7.62
     Ghana
    7.58
     Uganda
    7.45
     Cameroon
    7.41
     Kenya
    7.24
     Tanzania
    7.22
     Africans
    7.22
     Kenyan
    7.20
     Congo
    7.16
     Nigeria
    7.01
    Activations Density 0.615%

    No Known Activations