© 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. 16141
    Prev
    Next
    INDEX
    Explanations

    key features and characteristics of products or items being described

    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
    0:0.05
    1:0.06
    2:0.05
    3:0.05
    4:0.06
    5:0.10
    6:0.04
    7:0.07
    8:0.03
    9:0.32
    10:0.07
    11:0.04
    Negative Logits
    udeb
    -2.57
    heter
    -2.31
     derog
    -2.30
     abort
    -2.26
     blame
    -2.26
    wrong
    -2.18
     absentee
    -2.16
     interrupt
    -2.14
    erent
    -2.13
     cessation
    -2.13
    POSITIVE LOGITS
     Its
    4.06
     Built
    3.84
     Designed
    3.77
    Its
    3.71
    Built
    3.62
     Featuring
    3.38
     its
    3.29
     Located
    3.09
    Located
    3.07
    Created
    2.76
    Activations Density 0.600%

    No Known Activations