© 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. 5-ATT-KK
    11. 37834
    Prev
    Next
    INDEX
    Explanations

    phrases related to tensions and conflicts, particularly those involving international relations and human rights issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.19
    3:0.10
    4:0.06
    5:0.05
    6:0.04
    7:0.03
    8:0.05
    9:0.04
    10:0.15
    11:0.20
    Negative Logits
    ciation
    -1.54
    liest
    -1.24
    ois
    -1.22
    duino
    -1.14
    liner
    -1.11
    lear
    -1.10
     thereof
    -1.08
    ught
    -1.08
     guitar
    -1.07
    ttle
    -1.05
    POSITIVE LOGITS
     histories
    1.20
    igham
    1.20
     complicate
    1.16
     concentrated
    1.13
    utenberg
    1.11
     havens
    1.09
     ongoing
    1.09
     Dres
    1.09
     intertwined
    1.07
     Alleg
    1.07
    Activations Density 0.145%

    No Known Activations