© 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. 17125
    Prev
    Next
    INDEX
    Explanations

    phrases indicating complicity or involvement in actions or events

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

    No Comments

    Head Attr Weights
    0:0.03
    1:0.02
    2:0.06
    3:0.05
    4:0.11
    5:0.03
    6:0.06
    7:0.35
    8:0.03
    9:0.03
    10:0.08
    11:0.10
    Negative Logits
    azel
    -1.59
     VIDEOS
    -1.58
    ipment
    -1.55
    zers
    -1.51
    wow
    -1.47
    ipers
    -1.47
    itiz
    -1.47
    houses
    -1.46
    ocular
    -1.45
    enery
    -1.39
    POSITIVE LOGITS
     causation
    1.62
     piracy
    1.58
     wrongdoing
    1.55
     extortion
    1.52
     manslaughter
    1.49
     atrocities
    1.41
     Massacre
    1.41
     plotting
    1.38
     injustice
    1.37
     defeat
    1.36
    Activations Density 0.001%

    No Known Activations