© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 9801
    Prev
    Next
    INDEX
    Explanations

    phrases indicating ongoing investigations or serious allegations in political contexts

    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
    2:0.05
    3:0.02
    4:0.05
    5:0.03
    6:0.23
    7:0.04
    8:0.07
    9:0.32
    10:0.02
    11:0.03
    Negative Logits
     Asgard
    -4.29
     Hunts
    -4.25
     Musk
    -3.71
     Berk
    -3.59
     AWS
    -3.35
    uber
    -3.29
    ネ
    -3.28
     Swed
    -3.27
    Hun
    -3.26
     Panther
    -3.22
    POSITIVE LOGITS
     Di
    8.95
    Di
    7.87
    di
    7.20
     di
    6.09
     DI
    5.59
     Gi
    4.97
    DI
    4.92
    idi
    4.81
    Gi
    4.35
     Vic
    4.18
    Activations Density 0.012%

    No Known Activations