© 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. 38382
    Prev
    Next
    INDEX
    Explanations

    inflections and variations of the word "apply."

    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
    0:0.04
    1:0.04
    2:0.07
    3:0.04
    4:0.05
    5:0.04
    6:0.12
    7:0.31
    8:0.03
    9:0.03
    10:0.11
    11:0.05
    Negative Logits
     sidel
    -1.66
     dial
    -1.64
     answering
    -1.62
     unfocused
    -1.55
     forwarding
    -1.54
     tracker
    -1.53
     refining
    -1.50
     gears
    -1.46
     leak
    -1.45
    chel
    -1.44
    POSITIVE LOGITS
     Congratulations
    2.01
    owment
    1.85
    aez
    1.81
     laureate
    1.80
    eta
    1.69
    chance
    1.64
     Valhalla
    1.59
    winner
    1.54
    population
    1.48
     Participation
    1.46
    Activations Density 0.000%

    No Known Activations