© 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. 7422
    Prev
    Next
    INDEX
    Explanations

    instances of emotional expressions and thoughts

    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
    0:0.19
    1:0.09
    2:0.13
    3:0.08
    4:0.04
    5:0.03
    6:0.07
    7:0.07
    8:0.03
    9:0.04
    10:0.13
    11:0.04
    Negative Logits
     microw
    -3.83
     Kobe
    -3.31
     Thatcher
    -3.22
     Goldstein
    -3.19
     MPG
    -3.05
     Mous
    -3.03
    kb
    -3.01
     McF
    -2.99
     Boeing
    -2.98
     cand
    -2.98
    POSITIVE LOGITS
    River
    9.13
     River
    8.20
     river
    6.58
    river
    6.23
     Rivers
    5.82
     Rivera
    5.15
     rivers
    5.14
     downstream
    4.50
     Flood
    4.10
     raft
    4.09
    Activations Density 0.004%

    No Known Activations