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. 11234
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to political and governmental actions

    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
    1:0.03
    2:0.11
    3:0.04
    4:0.06
    5:0.03
    6:0.17
    7:0.06
    8:0.11
    9:0.21
    10:0.03
    11:0.03
    Negative Logits
     ger
    -3.48
    unicip
    -3.42
     Bohem
    -3.39
     seeded
    -3.36
    ijk
    -3.28
     seed
    -3.25
    ÃÂ
    -3.25
     Prague
    -3.20
     reprodu
    -3.15
    icro
    -3.14
    POSITIVE LOGITS
     Mattis
    10.15
    Matt
    6.62
     Matt
    4.66
     Tillerson
    4.51
     Duff
    3.91
     Marines
    3.85
     DEFENSE
    3.84
     Patton
    3.77
     Titans
    3.76
     Pentagon
    3.75
    Activations Density 0.003%

    No Known Activations