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

    Neuronpedia

    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. 10-ATT-KK
    11. 15031
    Prev
    Next
    INDEX
    Explanations

    references to FBI investigations and legal proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.17
    1:0.02
    2:0.06
    3:0.06
    4:0.06
    5:0.01
    6:0.27
    7:0.11
    8:0.01
    9:0.06
    10:0.06
    11:0.05
    Negative Logits
     councillors
    -3.00
     whales
    -2.73
     rugby
    -2.66
    obyl
    -2.66
     councillor
    -2.65
     Corsair
    -2.59
     Isles
    -2.54
     Rugby
    -2.53
     veto
    -2.52
     refere
    -2.48
    POSITIVE LOGITS
    FBI
    8.02
     FBI
    7.79
     bureau
    5.54
     Agents
    5.19
     Comey
    5.16
     ATF
    5.07
     agents
    4.96
     DOJ
    4.89
     Bureau
    4.62
     DEA
    4.57
    Activations Density 0.211%

    No Known Activations