© 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. 38066
    Prev
    Next
    INDEX
    Explanations

    specific events and trends in political or historical contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.05
    1:0.02
    2:0.17
    3:0.17
    4:0.08
    5:0.06
    6:0.02
    7:0.06
    8:0.04
    9:0.07
    10:0.12
    11:0.08
    Negative Logits
     dressing
    -1.31
     crush
    -1.28
     bully
    -1.24
     bullied
    -1.24
     complying
    -1.21
     infringing
    -1.20
     sweats
    -1.18
     intimidated
    -1.18
     Tah
    -1.17
     Firefly
    -1.16
    POSITIVE LOGITS
    方
    1.52
    oother
    1.42
    trak
    1.38
    ultimate
    1.35
     largeDownload
    1.28
     Ago
    1.24
    �
    1.19
    irin
    1.16
    igor
    1.16
    merce
    1.16
    Activations Density 0.110%

    No Known Activations