© 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. 12701
    Prev
    Next
    INDEX
    Explanations

    references to ongoing investigations and the complexities surrounding them

    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
    0:0.07
    1:0.29
    2:0.04
    3:0.03
    4:0.03
    5:0.02
    6:0.06
    7:0.11
    8:0.02
    9:0.03
    10:0.20
    11:0.05
    Negative Logits
     Ae
    -2.77
     cant
    -2.70
    ieu
    -2.59
    antine
    -2.54
     Fountain
    -2.52
    ppa
    -2.48
    alm
    -2.47
     Epic
    -2.46
    OUS
    -2.42
     Legendary
    -2.42
    POSITIVE LOGITS
     Whit
    8.85
    Whit
    8.56
     whit
    6.97
    wh
    4.28
     Whites
    3.65
    Wh
    3.59
     Whitman
    3.45
    White
    3.18
    white
    3.13
     White
    3.12
    Activations Density 0.007%

    No Known Activations