© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 5-ATT-KK
    11. 43079
    Prev
    Next
    INDEX
    Explanations

    terms related to Uighur culture and community

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.03
    1:0.05
    2:0.05
    3:0.06
    4:0.05
    5:0.06
    6:0.05
    7:0.04
    8:0.03
    9:0.10
    10:0.27
    11:0.15
    Negative Logits
    stay
    -1.42
     concentration
    -1.35
    rouse
    -1.29
    eno
    -1.26
    killers
    -1.25
     ―
    -1.21
     reportedly
    -1.21
     Signature
    -1.20
     occupies
    -1.19
     407
    -1.18
    POSITIVE LOGITS
     PowerShell
    1.63
    mone
    1.54
    natureconservancy
    1.44
     warranty
    1.43
     sermon
    1.42
    TeX
    1.42
     SEO
    1.39
    reprene
    1.37
    fold
    1.37
     homebrew
    1.36
    Activations Density 0.002%

    No Known Activations