© 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. 10-ATT-KK
    11. 23056
    Prev
    Next
    INDEX
    Explanations

    occurrences of proper nouns related to technology and significant figures in the tech industry

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    float32
    Hook Name
    blocks.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.11
    1:0.06
    2:0.07
    3:0.07
    4:0.04
    5:0.04
    6:0.08
    7:0.24
    8:0.02
    9:0.05
    10:0.10
    11:0.06
    Negative Logits
    Moon
    -2.51
    ��
    -2.49
    undo
    -2.46
    Fire
    -2.39
    uned
    -2.25
    闘
    -2.23
     Orche
    -2.23
    Meta
    -2.21
     Downtown
    -2.18
    Aud
    -2.18
    POSITIVE LOGITS
     Steph
    2.54
     Azerb
    2.34
     Somalia
    2.34
     Americ
    2.30
     Filip
    2.25
     recruiting
    2.24
     srf
    2.21
     patriotism
    2.15
     Pret
    2.13
     barracks
    2.10
    Activations Density 0.000%

    No Known Activations