© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 9-ATT-KK
    11. 14921
    Prev
    Next
    INDEX
    Explanations

    terms related to enhancements or improvements

    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
    1:0.03
    2:0.05
    3:0.06
    4:0.03
    5:0.05
    6:0.16
    7:0.05
    8:0.05
    9:0.32
    10:0.04
    11:0.04
    Negative Logits
     Rug
    -3.31
    Dick
    -3.15
     dispos
    -3.07
     rug
    -3.01
     Sle
    -3.01
    UID
    -2.92
    ick
    -2.85
     Dick
    -2.82
     Cran
    -2.82
    EW
    -2.81
    POSITIVE LOGITS
     translator
    5.62
     translation
    4.91
     Translation
    4.68
     translate
    4.50
    translation
    4.48
     translating
    4.39
     translated
    4.39
     transl
    4.38
    Translation
    4.28
     interpreter
    4.16
    Activations Density 0.000%

    No Known Activations