© 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. 19596
    Prev
    Next
    INDEX
    Explanations

    legislative language or proposals related to energy policies

    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
    0:0.25
    1:0.04
    2:0.04
    3:0.09
    4:0.03
    5:0.02
    6:0.08
    7:0.12
    8:0.01
    9:0.04
    10:0.18
    11:0.04
    Negative Logits
    ventus
    -3.54
     Shinji
    -3.45
     Rei
    -3.26
     Nero
    -3.23
     Sakuya
    -3.22
    Shin
    -3.20
    insula
    -3.15
     Juventus
    -3.13
    umbai
    -3.04
     Celtics
    -3.03
    POSITIVE LOGITS
     Wyoming
    9.22
     Yellowstone
    5.45
     Montana
    4.69
     Powder
    4.15
     Lar
    4.03
     Grizz
    3.93
     Zin
    3.90
     Idaho
    3.85
     Pryor
    3.79
    Colorado
    3.77
    Activations Density 0.003%

    No Known Activations