© 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. 15397
    Prev
    Next
    INDEX
    Explanations

    references to regulations and laws affecting industries and businesses

    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
    1:0.02
    2:0.03
    3:0.04
    4:0.07
    5:0.50
    6:0.01
    7:0.03
    8:0.01
    9:0.17
    10:0.02
    11:0.03
    Negative Logits
     blames
    -2.82
    MpServer
    -2.73
    quished
    -2.57
    76561
    -2.52
     accuses
    -2.49
     expires
    -2.48
    moil
    -2.45
     allege
    -2.40
     Dating
    -2.40
    �
    -2.39
    POSITIVE LOGITS
     without
    6.00
    without
    5.25
     quicker
    5.21
     easier
    5.15
     efficiently
    4.86
     faster
    4.76
     smoother
    4.69
     effortlessly
    4.55
     seamlessly
    4.42
     whilst
    4.33
    Activations Density 1.082%

    No Known Activations