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. 18631
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant historical events and figures

    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
    1:0.02
    2:0.10
    3:0.08
    4:0.02
    5:0.07
    6:0.05
    7:0.09
    8:0.31
    9:0.05
    10:0.04
    11:0.04
    Negative Logits
     Catalyst
    -3.43
    ajor
    -3.15
    arijuana
    -3.12
     Holder
    -3.11
     WB
    -3.10
    ////////////////
    -3.05
     Gilmore
    -3.04
    reen
    -3.04
    }{
    -3.02
     CBD
    -2.98
    POSITIVE LOGITS
     Napoleon
    6.95
    Nap
    4.80
     Frenchman
    4.39
     Trotsky
    4.27
     Bolshe
    4.18
     Mongolia
    4.17
     Mongol
    4.06
     Stalin
    3.98
     Alps
    3.90
    oleon
    3.88
    Activations Density 0.001%

    No Known Activations