© 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. 10-ATT-KK
    11. 8052
    Prev
    Next
    INDEX
    Explanations

    statements about verification or confirmation

    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
    0:0.09
    1:0.20
    2:0.05
    3:0.05
    4:0.04
    5:0.04
    6:0.05
    7:0.10
    8:0.05
    9:0.05
    10:0.18
    11:0.05
    Negative Logits
    ��
    -3.06
    cer
    -2.63
    cers
    -2.57
    cu
    -2.52
     grate
    -2.51
    uca
    -2.50
     Quartz
    -2.49
    Rose
    -2.46
     Oz
    -2.44
    ECD
    -2.42
    POSITIVE LOGITS
     Hind
    6.86
     Hath
    3.90
     hind
    3.44
    Sund
    3.42
     Hust
    3.30
    Lind
    3.26
     Jets
    3.25
     Lind
    3.11
     Lash
    3.04
     Til
    2.87
    Activations Density 0.002%

    No Known Activations