© 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. 22646
    Prev
    Next
    INDEX
    Explanations

    instances of assumption and mocking in discussions or critiques

    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
    0:0.18
    1:0.09
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.05
    7:0.10
    8:0.02
    9:0.05
    10:0.25
    11:0.05
    Negative Logits
     Jade
    -3.45
     Gemini
    -3.11
    irt
    -2.70
    IRT
    -2.70
     tant
    -2.64
     Agg
    -2.60
     cryst
    -2.58
    adr
    -2.57
     ≡
    -2.51
    cle
    -2.50
    POSITIVE LOGITS
     Wol
    10.39
    Wil
    4.27
     Wilmington
    4.00
     Schro
    3.91
     Pitt
    3.85
     Witt
    3.81
     WP
    3.80
     Wil
    3.72
     Wel
    3.71
     Wer
    3.59
    Activations Density 0.001%

    No Known Activations