© 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. 6491
    Prev
    Next
    INDEX
    Explanations

    references to corporate structures and partnerships

    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
    0:0.05
    1:0.03
    2:0.03
    3:0.08
    4:0.26
    5:0.06
    6:0.07
    7:0.10
    8:0.02
    9:0.13
    10:0.03
    11:0.09
    Negative Logits
     pretended
    -3.17
     bullshit
    -2.99
     slander
    -2.85
     gore
    -2.82
     shitty
    -2.81
    shit
    -2.78
     faked
    -2.78
     masturb
    -2.77
     grop
    -2.76
    bugs
    -2.75
    POSITIVE LOGITS
     innovative
    3.87
     exciting
    3.85
     excellence
    3.66
     exceptional
    3.59
     innovation
    3.50
     outstanding
    3.50
     pioneering
    3.49
     vibrant
    3.37
     groundbreaking
    3.34
     unparalleled
    3.27
    Activations Density 0.749%

    No Known Activations