© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 22029
    Prev
    Next
    INDEX
    Explanations

    phrases related to government accountability and scrutiny of agencies

    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
    0:0.18
    1:0.01
    2:0.21
    3:0.07
    4:0.02
    5:0.11
    6:0.05
    7:0.04
    8:0.17
    9:0.05
    10:0.02
    11:0.02
    Negative Logits
     Sebast
    -2.95
    hots
    -2.90
    imov
    -2.84
    vic
    -2.83
     aquatic
    -2.78
    razil
    -2.77
     Mali
    -2.75
    Atl
    -2.71
     submer
    -2.70
    arcity
    -2.68
    POSITIVE LOGITS
     IRS
    7.30
     Lerner
    5.39
     Lois
    4.40
     audits
    4.35
     FEC
    4.16
     taxpayers
    3.95
     Revenue
    3.94
     taxpayer
    3.91
     tax
    3.86
     501
    3.86
    Activations Density 0.049%

    No Known Activations