© 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. 7371
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to policies and regulations

    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
    0:0.02
    1:0.03
    2:0.05
    3:0.04
    4:0.06
    5:0.28
    6:0.04
    7:0.04
    8:0.02
    9:0.21
    10:0.02
    11:0.14
    Negative Logits
     resumes
    -2.90
    ometimes
    -2.56
    Suddenly
    -2.45
    pires
    -2.41
    ruciating
    -2.38
     learns
    -2.37
     overheard
    -2.33
     startled
    -2.33
    verages
    -2.31
     awoke
    -2.31
    POSITIVE LOGITS
     expansion
    3.03
    mination
    2.92
     amendment
    2.81
     despite
    2.76
     abolition
    2.76
    enthal
    2.72
    ¨
    2.54
     privatization
    2.52
     [+
    2.48
     implementation
    2.46
    Activations Density 0.129%

    No Known Activations