Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 3203
    Prev
    Next
    INDEX
    Explanations

    references to investigations and inquiries into deaths and causes of death

    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
    0:0.08
    1:0.03
    2:0.08
    3:0.04
    4:0.06
    5:0.05
    6:0.21
    7:0.05
    8:0.09
    9:0.21
    10:0.02
    11:0.04
    Negative Logits
    ilton
    -3.86
    ghost
    -3.78
    uliffe
    -3.46
     Klux
    -3.45
    Liber
    -3.41
    fl
    -3.29
     Jacksonville
    -3.28
    apeake
    -3.28
    Taylor
    -3.20
    incoln
    -3.19
    POSITIVE LOGITS
     Ara
    10.49
     Mats
    7.98
     Abbas
    5.27
     mats
    4.58
     Tsu
    4.50
     Fuk
    4.42
     Yas
    4.37
     Ib
    4.17
     Amin
    4.15
     Hau
    4.09
    Activations Density 0.001%

    No Known Activations