© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Under Peer Review · Attention SAE Research Paper
    5. GPT2-Small
    7. Attention Out
    9. 2-ATT-KK
    11. 11600
    Prev
    Next
    INDEX
    Explanations

    mentions of personnel guarding scenes or places

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.04
    1:0.04
    2:0.21
    3:0.05
    4:0.06
    5:0.11
    6:0.02
    7:0.04
    8:0.08
    9:0.20
    10:0.06
    11:0.04
    Negative Logits
    姫
    -1.70
    maxwell
    -1.42
    ional
    -1.36
    uld
    -1.32
     conception
    -1.29
    Bloom
    -1.29
     awa
    -1.28
    ertain
    -1.26
    reality
    -1.25
    ヴァ
    -1.24
    POSITIVE LOGITS
    stretched
    1.34
     Zub
    1.28
    rity
    1.27
     paramilitary
    1.24
    signed
    1.20
     Obi
    1.19
     flats
    1.19
     Thai
    1.17
     Amos
    1.17
     wrists
    1.16
    Activations Density 0.015%

    No Known Activations