© 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
    2. Under Peer Review · Attention SAE Research Paper
    3. GPT2-Small
    4. Attention Out
    5. 10-ATT-KK
    6. 15050
    Prev
    Next
    INDEX
    Explanations

    specific scientific and technical terms and references related to healthcare and research

    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
    0:0.05
    1:0.05
    2:0.08
    3:0.05
    4:0.04
    5:0.03
    6:0.05
    7:0.18
    8:0.04
    9:0.07
    10:0.25
    11:0.06
    Negative Logits
    zb
    -3.12
    haw
    -3.09
     裏�
    -3.05
    bern
    -3.02
     c
    -3.00
     Haley
    -2.93
    ン
    -2.86
    �
    -2.83
     ja
    -2.82
     裏覚醒
    -2.78
    POSITIVE LOGITS
    SPONSORED
    2.58
    RGB
    2.50
     exponential
    2.33
     polarized
    2.33
     unregulated
    2.32
     adaptive
    2.28
     W
    2.26
     placebo
    2.26
     antioxidant
    2.23
     Digest
    2.14
    Activations Density 0.134%

    No Known Activations