© 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. 47261
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and patterns of crime

    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
    1:0.02
    2:0.05
    3:0.03
    4:0.06
    5:0.03
    6:0.42
    7:0.05
    8:0.02
    9:0.04
    10:0.13
    11:0.09
    Negative Logits
    hiba
    -1.42
     Kills
    -1.31
    thumbnails
    -1.30
     Pradesh
    -1.29
    eni
    -1.28
    Unity
    -1.28
    usercontent
    -1.25
    *=-
    -1.23
    BIL
    -1.21
    iliary
    -1.19
    POSITIVE LOGITS
     looph
    1.55
    riage
    1.46
    enforcement
    1.41
     Lange
    1.39
    apple
    1.29
    arte
    1.26
     precedence
    1.25
     racket
    1.22
     precedent
    1.22
    ichick
    1.18
    Activations Density 0.020%

    No Known Activations