© 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. 39471
    Prev
    Next
    INDEX
    Explanations

    references to court verdicts and legal proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    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
    0:0.02
    1:0.01
    2:0.05
    3:0.06
    4:0.08
    5:0.03
    6:0.05
    7:0.33
    8:0.03
    9:0.04
    10:0.14
    11:0.09
    Negative Logits
     frequ
    -1.64
    yip
    -1.57
     Caf
    -1.55
     Gateway
    -1.46
    paces
    -1.45
     condu
    -1.41
     Travels
    -1.40
    archive
    -1.39
     Lif
    -1.37
    sites
    -1.35
    POSITIVE LOGITS
     verdict
    2.05
     guilty
    1.81
    ittal
    1.78
     manslaughter
    1.74
    llor
    1.67
    izoph
    1.61
     judgments
    1.53
     conviction
    1.51
     Guilty
    1.49
     decisively
    1.48
    Activations Density 0.002%

    No Known Activations