© 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. 23164
    Prev
    Next
    INDEX
    Explanations

    surnames of people

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    references to individuals with the last name "Das" or related phonetic patterns

    oai_token-act-pair · gpt-4o-mini
    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
    0:0.06
    1:0.04
    2:0.22
    3:0.09
    4:0.11
    5:0.08
    6:0.04
    7:0.03
    8:0.08
    9:0.11
    10:0.06
    11:0.03
    Negative Logits
    etheless
    -1.45
    theless
    -1.31
     FANTASY
    -1.28
    MAP
    -1.25
    VALUE
    -1.22
    cale
    -1.20
     CONTIN
    -1.17
    cffff
    -1.17
    SHIP
    -1.17
    NESS
    -1.15
    POSITIVE LOGITS
    hya
    1.31
     Soul
    1.12
    ��
    1.09
    utor
    1.08
    isable
    1.08
    ,"
    1.08
     Trace
    1.08
    gha
    1.05
     Nak
    1.05
     Wah
    1.03
    Activations Density 0.004%

    No Known Activations