© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 6674
    Prev
    Next
    INDEX
    Explanations

    phrases related to transitions and political appointments

    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
    0:0.23
    1:0.02
    2:0.19
    3:0.14
    4:0.03
    5:0.10
    6:0.03
    7:0.04
    8:0.08
    9:0.02
    10:0.04
    11:0.02
    Negative Logits
     collectors
    -2.37
     tram
    -2.31
     infring
    -2.24
    abiding
    -2.23
    obyl
    -2.21
     injustice
    -2.21
     collector
    -2.13
    heid
    -2.12
     Guinness
    -2.12
     licence
    -2.09
    POSITIVE LOGITS
     aides
    3.70
     confid
    3.66
     Kushner
    3.59
     advisers
    3.47
     Bannon
    3.43
     Manafort
    3.42
     Priebus
    3.37
     adviser
    3.15
     aide
    3.09
     advising
    3.01
    Activations Density 0.293%

    No Known Activations