© 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. 11403
    Prev
    Next
    INDEX
    Explanations

    phrases related to education, societal issues, and legal matters

    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
    1:0.01
    2:0.08
    3:0.07
    4:0.03
    5:0.17
    6:0.05
    7:0.08
    8:0.09
    9:0.05
    10:0.16
    11:0.08
    Negative Logits
    pires
    -1.10
    merce
    -1.07
     Releases
    -1.02
     transmissions
    -1.02
     Emails
    -0.98
     Realms
    -0.94
    vernment
    -0.94
     concedes
    -0.93
     assumes
    -0.93
     Masquerade
    -0.92
    POSITIVE LOGITS
    atered
    1.20
    itored
    1.06
    imming
    1.04
     tantal
    1.02
    orthy
    1.02
    irable
    1.02
    qqa
    0.98
    apest
    0.97
    rather
    0.97
    versible
    0.95
    Activations Density 0.592%

    No Known Activations