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. 3198
    Prev
    Next
    INDEX
    Explanations

    mentions of UN Secretary-General Ban Ki-moon and his calls for action

    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
    0:0.16
    1:0.02
    2:0.05
    3:0.16
    4:0.02
    5:0.05
    6:0.02
    7:0.04
    8:0.31
    9:0.03
    10:0.07
    11:0.02
    Negative Logits
     Kirin
    -3.24
     ALE
    -3.14
     Alexand
    -3.12
     Xander
    -3.07
     Coyotes
    -2.99
    amaz
    -2.95
     Lansing
    -2.89
    lyak
    -2.87
    Alex
    -2.80
     Yak
    -2.78
    POSITIVE LOGITS
     Belfast
    3.35
     Netherlands
    3.19
     Dutch
    3.19
     Jamaica
    3.17
     Ulster
    3.01
     Burma
    2.98
     Pound
    2.89
     Cambodia
    2.89
     Ireland
    2.85
     Fifa
    2.85
    Activations Density 0.000%

    No Known Activations