© 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
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 10-ATT-KK
    11. 15047
    Prev
    Next
    INDEX
    Explanations

    numerical values and product specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.11
    1:0.14
    2:0.12
    3:0.05
    4:0.04
    5:0.03
    6:0.04
    7:0.11
    8:0.03
    9:0.04
    10:0.18
    11:0.05
    Negative Logits
     Kand
    -3.04
     Robbins
    -2.92
     Shar
    -2.85
     Sal
    -2.78
     Mo
    -2.71
     Mur
    -2.64
     mir
    -2.63
     UAE
    -2.61
     Gamb
    -2.58
     WI
    -2.58
    POSITIVE LOGITS
     XL
    6.97
     XXX
    6.34
    XL
    6.23
     XX
    5.95
    XXX
    5.12
    XX
    5.01
     xx
    4.26
     LX
    4.06
    xx
    3.94
    YY
    3.65
    Activations Density 0.001%

    No Known Activations