© 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. 10-ATT-KK
    11. 6672
    Prev
    Next
    INDEX
    Explanations

    information related to criminal investigations and legal proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.08
    1:0.05
    2:0.06
    3:0.04
    4:0.04
    5:0.03
    6:0.26
    7:0.14
    8:0.02
    9:0.04
    10:0.11
    11:0.08
    Negative Logits
    fre
    -2.63
    Fre
    -2.55
    LIN
    -2.54
    MN
    -2.48
    GN
    -2.48
     referral
    -2.43
     AX
    -2.43
     TRE
    -2.42
    Letter
    -2.37
    trial
    -2.35
    POSITIVE LOGITS
    Poll
    7.73
     Poll
    7.29
    poll
    6.28
     poll
    6.06
     polls
    4.84
     polling
    4.25
     Vote
    3.78
     ballot
    3.54
     polled
    3.36
    Vote
    3.20
    Activations Density 0.011%

    No Known Activations