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. 11094
    Prev
    Next
    INDEX
    Explanations

    statements discussing conflicts and political positions

    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
    0:0.05
    1:0.03
    2:0.08
    3:0.04
    4:0.08
    5:0.04
    6:0.22
    7:0.07
    8:0.10
    9:0.17
    10:0.02
    11:0.05
    Negative Logits
     Pi
    -3.70
    Pi
    -3.67
    acco
    -3.65
    cone
    -3.40
     pi
    -3.39
    pi
    -3.37
     Sheridan
    -3.31
     Winston
    -3.26
     chi
    -3.20
     fmt
    -3.14
    POSITIVE LOGITS
     Saudi
    8.83
     Saudis
    8.76
    Saudi
    8.68
     Riyadh
    7.81
     Saud
    6.28
     Yemen
    6.20
     Houth
    6.16
     Yemeni
    6.08
     Arabia
    5.66
     Gulf
    5.39
    Activations Density 0.020%

    No Known Activations