© 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. 9-ATT-KK
    11. 17123
    Prev
    Next
    INDEX
    Explanations

    capital letters at the beginning of words, often indicating proper nouns or important concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_ds24576_bs4096_dc1.00e-06_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.9.attn.hook_z
    Hook Layer
    9
    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
    1:0.04
    2:0.05
    3:0.11
    4:0.07
    5:0.05
    6:0.26
    7:0.04
    8:0.04
    9:0.14
    10:0.03
    11:0.04
    Negative Logits
     Bie
    -3.16
     quir
    -3.05
     Gri
    -2.98
     Sans
    -2.85
     Sand
    -2.84
     Rap
    -2.83
     Pes
    -2.82
     Bust
    -2.81
     Mous
    -2.79
     Milk
    -2.79
    POSITIVE LOGITS
    itton
    3.22
    uliffe
    3.05
    isphere
    2.89
    uyomi
    2.75
    vier
    2.74
    renheit
    2.72
     Gallup
    2.69
    oscope
    2.62
     orderly
    2.60
     detectors
    2.57
    Activations Density 0.004%

    No Known Activations