© 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. 36995
    Prev
    Next
    INDEX
    Explanations

    phrases that express contradiction or division among people

    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
    1:0.02
    2:0.10
    3:0.12
    4:0.09
    5:0.02
    6:0.20
    7:0.08
    8:0.04
    9:0.03
    10:0.09
    11:0.12
    Negative Logits
     predecessor
    -1.21
     wal
    -1.11
     legend
    -1.09
     ancestor
    -1.07
    izational
    -1.07
     suprem
    -1.07
     alias
    -1.06
     minimalist
    -1.05
    TM
    -1.05
     reminiscent
    -1.04
    POSITIVE LOGITS
    iuses
    1.46
     batted
    1.44
    mbuds
    1.40
     interven
    1.38
     anymore
    1.37
    payer
    1.33
     Huma
    1.33
    giene
    1.33
     Flavoring
    1.30
    votes
    1.28
    Activations Density 0.026%

    No Known Activations