© 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. 39685
    Prev
    Next
    INDEX
    Explanations

    references to individuals and organizations involved in academic and bureaucratic contexts

    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
    0:0.01
    1:0.01
    2:0.11
    3:0.10
    4:0.41
    5:0.01
    6:0.04
    7:0.04
    8:0.05
    9:0.04
    10:0.06
    11:0.06
    Negative Logits
    ignty
    -1.62
    iage
    -1.61
    existence
    -1.56
    trak
    -1.53
    roo
    -1.50
     Serving
    -1.47
    ipation
    -1.40
    enery
    -1.39
     fitt
    -1.37
    nect
    -1.35
    POSITIVE LOGITS
     analyst
    1.59
     analysts
    1.58
     spokeswoman
    1.58
     reviewers
    1.55
     spokesman
    1.54
     interviewer
    1.53
    pedia
    1.50
     chemist
    1.50
     onlook
    1.48
     Gamer
    1.47
    Activations Density 0.340%

    No Known Activations