© 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. 29114
    Prev
    Next
    INDEX
    Explanations

    instances of high importance or emphasis in a discussion

    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
    0:0.02
    1:0.03
    2:0.06
    3:0.12
    4:0.07
    5:0.06
    6:0.09
    7:0.03
    8:0.09
    9:0.12
    10:0.12
    11:0.14
    Negative Logits
     electoral
    -1.92
     democr
    -1.89
     comprom
    -1.83
     campaign
    -1.77
     diplomatic
    -1.77
     leadership
    -1.65
     impeachment
    -1.64
     secession
    -1.63
     political
    -1.62
     Electoral
    -1.60
    POSITIVE LOGITS
    english
    1.52
    Phys
    1.50
     guiActiveUnfocused
    1.47
     Loft
    1.41
    olon
    1.38
    ometimes
    1.38
    Legendary
    1.37
    っ
    1.35
    ixtape
    1.34
    duration
    1.33
    Activations Density 0.072%

    No Known Activations