© 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. 23637
    Prev
    Next
    INDEX
    Explanations

    references to authorities and official entities

    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
    0:0.04
    1:0.01
    2:0.03
    3:0.17
    4:0.02
    5:0.03
    6:0.01
    7:0.03
    8:0.02
    9:0.01
    10:0.55
    11:0.02
    Negative Logits
    by
    -3.88
     by
    -3.10
     BY
    -3.03
     By
    -3.01
    By
    -2.94
    BY
    -2.54
    hello
    -2.48
    stood
    -2.42
    bys
    -2.38
    terness
    -2.12
    POSITIVE LOGITS
    :{
    2.08
     onto
    2.04
    rompt
    1.98
    ochet
    1.92
    ELF
    1.91
    azon
    1.89
    ographers
    1.89
    urai
    1.81
     forces
    1.78
     consecut
    1.77
    Activations Density 0.607%

    No Known Activations