© 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. 3-ATT-KK
    11. 14236
    Prev
    Next
    INDEX
    Explanations

    descriptions related to physical appearance, financial transactions, and digital content

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    descriptors related to physical attributes and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L3_Hcat_z_lr1.20e-03_l19.00e-01_ds24576_bs4096_dc1.00e-06_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.3.attn.hook_z
    Hook Layer
    3
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.03
    2:0.08
    3:0.07
    4:0.02
    5:0.02
    6:0.13
    7:0.28
    8:0.08
    9:0.03
    10:0.05
    11:0.14
    Negative Logits
     Directorate
    -1.17
    idated
    -1.01
    adjusted
    -1.00
     Blueprint
    -0.99
     carnage
    -0.95
     flux
    -0.95
     unanim
    -0.94
    ğ
    -0.94
     Coy
    -0.94
     millenn
    -0.93
    POSITIVE LOGITS
    haps
    1.21
     lashes
    1.19
    rush
    1.12
     (<
    1.09
    notations
    1.08
    poon
    1.08
    milo
    1.04
    itu
    1.02
    ographical
    1.01
     rh
    1.01
    Activations Density 0.029%

    No Known Activations