© 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. 10-ATT-KK
    11. 7386
    Prev
    Next
    INDEX
    Explanations

    information related to military operations and civilian casualties in Mosul

    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
    0:0.23
    1:0.02
    2:0.05
    3:0.07
    4:0.07
    5:0.02
    6:0.10
    7:0.19
    8:0.01
    9:0.05
    10:0.10
    11:0.04
    Negative Logits
     Vermont
    -4.06
     Taiwanese
    -3.44
     Guatem
    -3.41
     Nicarag
    -3.33
     Nicaragua
    -3.30
     Taiwan
    -3.20
     Laos
    -3.20
     Morales
    -3.19
     Ventura
    -3.14
     Dominican
    -3.11
    POSITIVE LOGITS
     Mosul
    6.10
     Iraqi
    4.86
     Baghdad
    4.37
     Raqqa
    4.33
    Iraq
    4.24
    Mos
    4.10
     ISIL
    4.06
     Kurdish
    3.93
     Pesh
    3.89
    Islamic
    3.81
    Activations Density 0.022%

    No Known Activations