© 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. 5239
    Prev
    Next
    INDEX
    Explanations

    technical instructions or details related to a specific process or product

    oai_token-act-pair · gpt-3.5-turbo
    Triggered 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
    Head Attr Weights
    0:0.06
    1:0.06
    2:0.13
    3:0.12
    4:0.04
    5:0.04
    6:0.09
    7:0.12
    8:0.07
    9:0.07
    10:0.09
    11:0.05
    Negative Logits
    furt
    -1.27
    intent
    -1.23
     behavi
    -1.22
    untled
    -1.13
     conflic
    -1.11
     redes
    -1.09
     encount
    -1.09
    aido
    -1.07
    usky
    -1.03
    udeb
    -1.02
    POSITIVE LOGITS
    −
    1.17
     brackets
    1.11
     Pt
    1.05
     parentheses
    1.03
    minus
    0.96
     equivalents
    0.95
    �
    0.94
    illion
    0.94
     β
    0.94
     fig
    0.92
    Activations Density 0.004%

    No Known Activations