© 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. 21840
    Prev
    Next
    INDEX
    Explanations

    references to legal or criminal activities involving individuals and specific incidents

    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
    0:0.02
    1:0.01
    2:0.10
    3:0.12
    4:0.16
    5:0.02
    6:0.04
    7:0.19
    8:0.05
    9:0.04
    10:0.07
    11:0.12
    Negative Logits
    employed
    -1.46
     indeed
    -1.45
     Examination
    -1.37
     recomp
    -1.36
     SAR
    -1.34
     deposited
    -1.33
    itialized
    -1.32
    eret
    -1.30
     unemploy
    -1.29
     depos
    -1.29
    POSITIVE LOGITS
    zsche
    1.50
    bane
    1.49
    vale
    1.41
    ァ
    1.40
     kW
    1.29
     Holt
    1.29
     Pulse
    1.28
    ande
    1.27
     Whip
    1.23
    pell
    1.22
    Activations Density 0.003%

    No Known Activations