© 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. 38388
    Prev
    Next
    INDEX
    Explanations

    references to political processes and decision-making outcomes

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.01
    2:0.07
    3:0.14
    4:0.06
    5:0.08
    6:0.02
    7:0.03
    8:0.10
    9:0.13
    10:0.18
    11:0.10
    Negative Logits
     Vaugh
    -1.32
     skelet
    -1.27
     aliases
    -1.25
     distingu
    -1.23
     suspic
    -1.22
     ancest
    -1.19
     Mehran
    -1.17
     alias
    -1.12
     photograp
    -1.12
    entimes
    -1.11
    POSITIVE LOGITS
    TPP
    1.58
     Liberals
    1.42
    morrow
    1.39
     Conservatives
    1.34
     sooner
    1.27
     majorities
    1.26
     progressives
    1.24
     Treaty
    1.24
     Republicans
    1.21
     loopholes
    1.21
    Activations Density 1.123%

    No Known Activations