© 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. 14558
    Prev
    Next
    INDEX
    Explanations

    policy decisions or declarations

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

    instances of contracts, policies, and administrative decisions being revoked or amended

    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
    1:0.03
    2:0.06
    3:0.15
    4:0.03
    5:0.04
    6:0.04
    7:0.11
    8:0.09
    9:0.14
    10:0.07
    11:0.17
    Negative Logits
    Streamer
    -1.30
    urus
    -1.16
    ixture
    -1.15
    ixtures
    -1.14
     ripe
    -1.08
    ould
    -1.08
    hov
    -1.07
    iculture
    -1.07
    chem
    -1.06
    ère
    -1.06
    POSITIVE LOGITS
     libel
    1.31
     eligibility
    1.26
     affiliation
    1.10
     oath
    1.08
     apology
    1.02
    Repeat
    1.02
     allegiance
    1.02
     outright
    1.02
     draconian
    1.01
     tresp
    1.01
    Activations Density 0.005%

    No Known Activations