© 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. 9-ATT-KK
    11. 3533
    Prev
    Next
    INDEX
    Explanations

    references to detainees and their treatment

    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
    1:0.02
    2:0.20
    3:0.06
    4:0.03
    5:0.08
    6:0.03
    7:0.07
    8:0.17
    9:0.04
    10:0.04
    11:0.04
    Negative Logits
    amac
    -3.00
     Minion
    -2.98
     Dorothy
    -2.80
    hester
    -2.73
     tornado
    -2.71
     Irma
    -2.70
     Wicked
    -2.66
     Asheville
    -2.62
     Elise
    -2.49
     Lansing
    -2.49
    POSITIVE LOGITS
     detainees
    4.23
     detainee
    4.05
     indefinite
    3.54
     Abu
    3.54
     Guantanamo
    3.46
     Guant
    3.26
     detention
    3.19
     Dubai
    3.05
     UAE
    2.98
     interrog
    2.90
    Activations Density 0.004%

    No Known Activations