© 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. 10-ATT-KK
    11. 13549
    Prev
    Next
    INDEX
    Explanations

    words related to extreme or significant events or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.09
    1:0.07
    2:0.07
    3:0.08
    4:0.08
    5:0.08
    6:0.08
    7:0.08
    8:0.07
    9:0.09
    10:0.08
    11:0.09
    Negative Logits
     cler
    -2.58
    illac
    -2.42
     sincerity
    -2.39
     reconciliation
    -2.38
     contracted
    -2.35
     resur
    -2.33
     combustion
    -2.29
     brid
    -2.28
     Tracy
    -2.28
     pont
    -2.27
    POSITIVE LOGITS
     ASUS
    2.73
    SpaceEngineers
    2.71
    HUD
    2.65
     Maiden
    2.61
     Vest
    2.61
    (&
    2.59
     Gundam
    2.54
     NEO
    2.48
     Obst
    2.47
    Kick
    2.46
    Activations Density 0.000%

    No Known Activations