© 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. 9-ATT-KK
    11. 6401
    Prev
    Next
    INDEX
    Explanations

    statements that indicate potential changes in policies or agreements related to business, trade, and international relations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L9_Hcat_z_lr1.20e-03_l11.20e+00_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.9.attn.hook_z
    Hook Layer
    9
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.02
    2:0.05
    3:0.03
    4:0.05
    5:0.03
    6:0.22
    7:0.04
    8:0.04
    9:0.28
    10:0.03
    11:0.04
    Negative Logits
     Pearce
    -4.00
    HUD
    -3.77
    iframe
    -3.73
     Brennan
    -3.70
    andi
    -3.56
     nest
    -3.55
    emb
    -3.45
    aley
    -3.44
    iddled
    -3.42
     Bridge
    -3.38
    POSITIVE LOGITS
     Vol
    9.63
    Vol
    9.28
    vol
    8.47
     VOL
    8.06
    VOL
    7.58
     vol
    7.24
     Volvo
    5.93
     Volume
    5.49
    Volume
    5.33
     Volcano
    4.97
    Activations Density 0.004%

    No Known Activations