© 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. 23252
    Prev
    Next
    INDEX
    Explanations

    references to locations and allegations associated with political or legal matters

    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
    0:0.03
    1:0.02
    2:0.03
    3:0.04
    4:0.06
    5:0.11
    6:0.04
    7:0.03
    8:0.01
    9:0.51
    10:0.02
    11:0.06
    Negative Logits
     whence
    -2.37
     where
    -2.24
     transitions
    -2.22
     coordinates
    -2.04
     chooses
    -2.04
     Moves
    -2.00
     layout
    -2.00
     experience
    -1.99
     performs
    -1.97
     Creat
    -1.95
    POSITIVE LOGITS
    against
    4.83
     against
    4.06
     Against
    3.45
    Against
    3.17
     lodged
    2.96
     alleging
    2.87
     outwe
    2.73
    about
    2.51
     surfaced
    2.49
     accuser
    2.47
    Activations Density 0.246%

    No Known Activations