© 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. 16045
    Prev
    Next
    INDEX
    Explanations

    words related to violent events and conflict, especially in relation to certain regions

    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
    0:0.07
    1:0.15
    2:0.05
    3:0.08
    4:0.03
    5:0.08
    6:0.11
    7:0.08
    8:0.06
    9:0.07
    10:0.12
    11:0.06
    Negative Logits
     someday
    -1.72
    ��
    -1.55
     wellness
    -1.55
    Too
    -1.54
    ~~~~
    -1.53
    STEM
    -1.51
    Favorite
    -1.47
    Measure
    -1.47
     blah
    -1.46
     crappy
    -1.44
    POSITIVE LOGITS
     ceasefire
    2.25
     armoured
    1.97
     seized
    1.83
     Rohingya
    1.80
     Syrian
    1.75
     Nato
    1.75
     truce
    1.74
     Libyan
    1.74
     Syrians
    1.73
     Sudan
    1.73
    Activations Density 0.480%

    No Known Activations