© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 17302
    Prev
    Next
    INDEX
    Explanations

    references to specific mechanical components or devices

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.11
    1:0.10
    2:0.08
    3:0.05
    4:0.06
    5:0.06
    6:0.07
    7:0.08
    8:0.05
    9:0.08
    10:0.16
    11:0.05
    Negative Logits
     Mog
    -2.75
     EB
    -2.73
    rip
    -2.60
     Yanukovych
    -2.54
     metic
    -2.52
     haste
    -2.51
     velvet
    -2.46
    rog
    -2.42
     prostitute
    -2.41
     volley
    -2.40
    POSITIVE LOGITS
     Dai
    8.52
     Kai
    3.70
     Hai
    3.59
     Dak
    3.48
     Bai
    3.42
    ai
    3.38
    hai
    3.36
    ichi
    3.34
     Sai
    3.29
    �
    3.26
    Activations Density 0.000%

    No Known Activations