© 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. 2303
    Prev
    Next
    INDEX
    Explanations

    information about civilian casualties and humanitarian crises in conflict zones

    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
    0:0.08
    1:0.01
    2:0.23
    3:0.15
    4:0.03
    5:0.13
    6:0.01
    7:0.09
    8:0.11
    9:0.01
    10:0.06
    11:0.02
    Negative Logits
     Patent
    -2.42
     induct
    -2.27
     Bonds
    -2.26
    OPA
    -2.20
     Gins
    -2.18
    Madison
    -2.09
    Adams
    -2.04
     plagiar
    -2.03
     patent
    -2.02
    asonic
    -2.01
    POSITIVE LOGITS
     UNHCR
    3.58
     evacuated
    3.55
     evac
    3.53
     evacuation
    3.52
     displaced
    3.43
     looted
    3.34
     refugees
    3.27
     tents
    3.25
     rubble
    3.24
     survivors
    3.23
    Activations Density 0.678%

    No Known Activations