© 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. 15880
    Prev
    Next
    INDEX
    Explanations

    topics related to political events and figures

    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
    0:0.02
    1:0.01
    2:0.02
    3:0.04
    4:0.28
    5:0.27
    6:0.01
    7:0.02
    8:0.01
    9:0.21
    10:0.01
    11:0.02
    Negative Logits
     [/
    -3.95
    .</
    -3.81
    .):
    -3.52
    !.
    -3.48
    [/
    -3.42
    !:
    -3.40
     🙂
    -3.30
    ':
    -3.21
    >.
    -3.19
    >:
    -3.18
    POSITIVE LOGITS
     unsuccessfully
    2.52
    BuyableInstoreAndOnline
    2.38
    ymm
    2.38
    quartered
    2.25
     meanwhile
    2.24
     nicknamed
    2.22
    phalt
    2.22
    inez
    2.17
     earlier
    2.15
    inventoryQuantity
    2.14
    Activations Density 0.176%

    No Known Activations