© 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. 38090
    Prev
    Next
    INDEX
    Explanations

    phrases related to law enforcement and fugitives

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.01
    1:0.01
    2:0.06
    3:0.08
    4:0.10
    5:0.03
    6:0.05
    7:0.32
    8:0.03
    9:0.04
    10:0.13
    11:0.09
    Negative Logits
    rompt
    -1.51
    olicy
    -1.40
    DragonMagazine
    -1.36
    rescent
    -1.36
     aisle
    -1.36
    idences
    -1.35
    imeo
    -1.34
     coaster
    -1.34
    ventures
    -1.34
     cynicism
    -1.33
    POSITIVE LOGITS
     fel
    1.53
     Naj
    1.46
    orers
    1.45
    oker
    1.42
    ��
    1.40
    emort
    1.37
    awar
    1.36
    oval
    1.34
    ynski
    1.33
     Kand
    1.32
    Activations Density 0.001%

    No Known Activations