© 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. 14294
    Prev
    Next
    INDEX
    Explanations

    phrases related to abstract concepts and formal language

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

    relationships between concepts involving dualities and contrasts

    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
    0:0.03
    1:0.06
    2:0.15
    3:0.07
    4:0.03
    5:0.05
    6:0.07
    7:0.10
    8:0.14
    9:0.05
    10:0.12
    11:0.07
    Negative Logits
    irlf
    -0.95
    EEK
    -0.89
    eport
    -0.87
    tch
    -0.86
    querade
    -0.86
    emp
    -0.83
     recess
    -0.79
    emi
    -0.78
    EMP
    -0.77
    ebin
    -0.76
    POSITIVE LOGITS
     alike
    1.32
     ↑
    1.02
     organisms
    0.82
    ppings
    0.81
     ‎
    0.81
     attendant
    0.80
    rities
    0.80
    terness
    0.80
     respectively
    0.79
    isms
    0.79
    Activations Density 0.201%

    No Known Activations