© 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. 4552
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, including names and roles

    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
    0:0.05
    1:0.02
    2:0.03
    3:0.06
    4:0.06
    5:0.04
    6:0.11
    7:0.03
    8:0.03
    9:0.47
    10:0.02
    11:0.04
    Negative Logits
    URE
    -3.01
     Yao
    -2.95
    034
    -2.88
    Hide
    -2.87
    ENE
    -2.84
     Mehran
    -2.81
     Hoo
    -2.77
     Ara
    -2.74
    UNE
    -2.73
     Rupert
    -2.68
    POSITIVE LOGITS
    xual
    4.18
    kl
    3.92
     Dh
    3.88
    gb
    3.86
    dh
    3.82
    kb
    3.80
    dk
    3.74
    qv
    3.71
    nb
    3.67
    mc
    3.62
    Activations Density 0.136%

    No Known Activations