© 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. 16186
    Prev
    Next
    INDEX
    Explanations

    quotes and statements indicating speculation or doubt

    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
    0:0.20
    1:0.13
    2:0.13
    3:0.05
    4:0.03
    5:0.02
    6:0.10
    7:0.10
    8:0.02
    9:0.02
    10:0.11
    11:0.03
    Negative Logits
    Cub
    -3.35
     Nixon
    -3.31
    oslov
    -3.30
     Nak
    -3.29
    kefeller
    -3.06
    MpServer
    -3.04
     Oswald
    -3.04
     Panasonic
    -2.88
     µ
    -2.86
     Hubble
    -2.82
    POSITIVE LOGITS
     Brandon
    8.16
    Brandon
    7.84
     Rapids
    3.66
     Bradley
    3.29
     Jaime
    3.22
     Vander
    3.19
     Jace
    3.08
     Kyle
    3.05
     wildfire
    3.05
     Brad
    3.03
    Activations Density 0.003%

    No Known Activations