© 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. 13040
    Prev
    Next
    INDEX
    Explanations

    internet domain mentions and references to significant individuals

    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
    0:0.26
    1:0.04
    2:0.04
    3:0.07
    4:0.08
    5:0.03
    6:0.06
    7:0.13
    8:0.02
    9:0.03
    10:0.08
    11:0.11
    Negative Logits
     Lenovo
    -3.22
    aroo
    -3.04
     Fiat
    -3.02
     hippocamp
    -2.94
     Nvidia
    -2.92
    Gamer
    -2.84
    inelli
    -2.78
     Venice
    -2.75
    ierrez
    -2.75
    awi
    -2.74
    POSITIVE LOGITS
     meteor
    8.01
     Meteor
    7.36
     mete
    5.95
     comet
    5.37
    eor
    5.19
     Comet
    4.57
     asteroids
    4.32
     asteroid
    4.03
     Perse
    3.99
     fireball
    3.97
    Activations Density 0.011%

    No Known Activations