© 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. 14290
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal matters and political statements

    oai_token-act-pair · gpt-3.5-turbo
    Triggered by @bot

    phrases related to legal and political accountability

    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
    0:0.04
    1:0.07
    2:0.06
    3:0.02
    4:0.06
    5:0.35
    6:0.05
    7:0.04
    8:0.07
    9:0.06
    10:0.07
    11:0.04
    Negative Logits
    ixt
    -1.92
     resided
    -1.89
    urgical
    -1.86
    pite
    -1.81
    wards
    -1.80
    kered
    -1.75
    rived
    -1.74
     contiguous
    -1.72
     semblance
    -1.70
     consolidated
    -1.69
    POSITIVE LOGITS
    enegger
    2.60
     advises
    2.20
     Adds
    2.19
     Advice
    2.02
     warns
    1.94
     recommends
    1.93
    Adds
    1.91
     blames
    1.84
     thinks
    1.83
     guides
    1.82
    Activations Density 0.397%

    No Known Activations