© 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. 16005
    Prev
    Next
    INDEX
    Explanations

    proper nouns of names

    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
    0:0.03
    1:0.03
    2:0.06
    3:0.07
    4:0.03
    5:0.12
    6:0.09
    7:0.08
    8:0.14
    9:0.06
    10:0.15
    11:0.08
    Negative Logits
     aggress
    -0.96
     congr
    -0.82
     Predator
    -0.82
     retarded
    -0.79
     ab
    -0.78
     gen
    -0.78
     ordinary
    -0.77
     Pak
    -0.77
     disag
    -0.77
     appe
    -0.77
    POSITIVE LOGITS
    ogun
    1.21
    ================================================================
    1.17
    mosp
    1.02
     WATCHED
    1.01
    andals
    1.01
    rovers
    1.00
    onut
    0.99
    ══
    0.97
    obyl
    0.96
    urches
    0.94
    Activations Density 0.080%

    No Known Activations