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. 11235
    Prev
    Next
    INDEX
    Explanations

    references to investigations and legal proceedings related to Donald Trump and Robert Mueller's probe

    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
    0:0.27
    1:0.01
    2:0.22
    3:0.06
    4:0.04
    5:0.09
    6:0.02
    7:0.05
    8:0.13
    9:0.02
    10:0.03
    11:0.02
    Negative Logits
    ufact
    -2.67
     Dh
    -2.62
    culosis
    -2.56
    BOOK
    -2.54
     Zoro
    -2.42
    icket
    -2.38
     Wah
    -2.36
     condoms
    -2.36
    eworld
    -2.34
     Printed
    -2.33
    POSITIVE LOGITS
     Mueller
    5.40
    ueller
    4.60
     Manafort
    4.16
     indict
    3.93
     Rosenstein
    3.89
     subpoen
    3.74
    FBI
    3.68
     indicted
    3.68
     probing
    3.45
     subpoena
    3.33
    Activations Density 0.015%

    No Known Activations