© 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. 10-ATT-KK
    11. 8411
    Prev
    Next
    INDEX
    Explanations

    terms related to legal or academic disputes and the consequences that arise from them

    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
    0:0.14
    1:0.14
    2:0.04
    3:0.04
    4:0.03
    5:0.02
    6:0.06
    7:0.08
    8:0.02
    9:0.03
    10:0.32
    11:0.04
    Negative Logits
     cc
    -3.51
     Mae
    -3.20
     quad
    -3.08
     OB
    -3.00
    anke
    -2.97
    gc
    -2.96
     DX
    -2.90
     Booth
    -2.90
     Bowman
    -2.83
    ocular
    -2.75
    POSITIVE LOGITS
     Sal
    9.98
    Sal
    8.89
     sal
    7.96
    sal
    7.71
     SAL
    7.65
     Salam
    6.87
     Salman
    5.14
    Salt
    5.10
     Salt
    4.95
     salt
    4.93
    Activations Density 0.047%

    No Known Activations