© 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. 5498
    Prev
    Next
    INDEX
    Explanations

    references to people and their interactions in specific contexts

    oai_token-act-pair · gpt-4o-mini
    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
    0:0.02
    1:0.06
    2:0.10
    3:0.04
    4:0.01
    5:0.03
    6:0.09
    7:0.09
    8:0.13
    9:0.05
    10:0.07
    11:0.26
    Negative Logits
     Ki
    -1.31
    ani
    -1.18
     Citation
    -1.10
    assi
    -1.10
     Hes
    -1.07
     Aid
    -1.02
    ocative
    -1.01
     Ig
    -0.99
    amba
    -0.99
     kindly
    -0.98
    POSITIVE LOGITS
    SQL
    1.37
    ه
    1.31
     rewritten
    1.21
    URN
    1.17
    kill
    1.14
    FIN
    1.13
    ynthesis
    1.08
    OHN
    1.07
     nerv
    1.05
     chars
    1.04
    Activations Density 0.023%

    No Known Activations