© 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. 5-ATT-KK
    11. 10297
    Prev
    Next
    INDEX
    Explanations

    instances of criminal charges and arrests

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 5-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.22
    1:0.17
    2:0.10
    3:0.04
    4:0.04
    5:0.09
    6:0.03
    7:0.03
    8:0.05
    9:0.07
    10:0.06
    11:0.06
    Negative Logits
    LINE
    -1.99
    Chicken
    -1.94
    バ
    -1.83
    Par
    -1.81
    BBC
    -1.80
    Phase
    -1.77
    XXX
    -1.77
    Salt
    -1.75
    slave
    -1.73
    Methods
    -1.68
    POSITIVE LOGITS
    ierrez
    2.14
    enegger
    2.06
     rejo
    2.01
    dayName
    1.85
     nodding
    1.80
     reacts
    1.80
    eele
    1.77
    oglu
    1.77
     pled
    1.73
     defended
    1.72
    Activations Density 0.003%

    No Known Activations