© 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. 2-ATT-KK
    11. 11519
    Prev
    Next
    INDEX
    Explanations

    academic and scholarly references related to various fields such as medicine, management, and pediatrics

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L2_Hcat_z_lr1.20e-03_l11.00e+00_ds24576_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v4.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.2.attn.hook_z
    Hook Layer
    2
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.05
    1:0.03
    2:0.20
    3:0.05
    4:0.28
    5:0.04
    6:0.03
    7:0.02
    8:0.06
    9:0.10
    10:0.05
    11:0.02
    Negative Logits
    meal
    -1.66
    onyms
    -1.48
    irlwind
    -1.46
    ogether
    -1.39
    ィ
    -1.37
    imir
    -1.36
    neau
    -1.35
    together
    -1.33
    pool
    -1.31
    aways
    -1.29
    POSITIVE LOGITS
     Ethics
    1.54
     Style
    1.47
     Nobel
    1.45
     honors
    1.42
     Responsibility
    1.41
     Literature
    1.40
     Directors
    1.39
    redits
    1.38
     alum
    1.37
     GOT
    1.36
    Activations Density 0.004%

    No Known Activations