© 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. 25896
    Prev
    Next
    INDEX
    Explanations

    phrases related to diplomatic relations and their status between countries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    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
    0:0.03
    1:0.01
    2:0.12
    3:0.08
    4:0.07
    5:0.04
    6:0.03
    7:0.04
    8:0.04
    9:0.05
    10:0.30
    11:0.13
    Negative Logits
    pse
    -1.55
    gaard
    -1.44
    ograph
    -1.44
    sample
    -1.43
     Canaver
    -1.41
    rand
    -1.40
    wave
    -1.39
    random
    -1.38
    lambda
    -1.37
     Rak
    -1.36
    POSITIVE LOGITS
     insepar
    1.99
     comr
    1.81
     bilateral
    1.64
     heightened
    1.53
    ;;;;;;;;;;;;
    1.50
     engagement
    1.48
     deepening
    1.42
    interrupted
    1.42
    avering
    1.42
     sustained
    1.41
    Activations Density 0.050%

    No Known Activations