© 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. 30036
    Prev
    Next
    INDEX
    Explanations

    terms related to anonymity and identity within the context of surveillance or security

    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
    0:0.03
    1:0.01
    2:0.05
    3:0.06
    4:0.14
    5:0.04
    6:0.04
    7:0.36
    8:0.03
    9:0.04
    10:0.09
    11:0.06
    Negative Logits
    raltar
    -1.89
     reimburse
    -1.84
     allowance
    -1.74
    burse
    -1.71
    232
    -1.68
    anty
    -1.66
    exclusive
    -1.65
    urances
    -1.64
    880
    -1.63
    urance
    -1.62
    POSITIVE LOGITS
     mysteries
    1.64
     plagiar
    1.59
     suspects
    1.53
     dark
    1.52
     Spoiler
    1.50
     cryptic
    1.50
     lur
    1.50
     Evil
    1.50
     hoax
    1.49
     mystery
    1.48
    Activations Density 0.000%

    No Known Activations