© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 9-ATT-KK
    6. 11113
    Prev
    Next
    INDEX
    Explanations

    references to research institutions and their contributions

    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
    0:0.06
    1:0.02
    2:0.08
    3:0.08
    4:0.03
    5:0.07
    6:0.07
    7:0.04
    8:0.40
    9:0.07
    10:0.03
    11:0.02
    Negative Logits
    Alabama
    -5.21
     Alabama
    -4.78
     Clemson
    -4.34
     Redskins
    -4.25
     Confederate
    -4.01
    Tenn
    -3.97
     Auburn
    -3.82
    Virginia
    -3.77
     Tennessee
    -3.75
     Grayson
    -3.71
    POSITIVE LOGITS
     Swiss
    8.38
     Switzerland
    7.95
     Zurich
    7.48
     franc
    5.51
     Alps
    5.39
     Austrian
    5.35
     Austria
    5.03
     Alpine
    4.82
     Geneva
    4.66
     Luxembourg
    4.61
    Activations Density 0.026%

    No Known Activations