© 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. 5270
    Prev
    Next
    INDEX
    Explanations

    phrases related to controversial topics or news articles

    oai_token-act-pair · gpt-3.5-turbo
    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
    0:0.05
    1:0.07
    2:0.05
    3:0.10
    4:0.03
    5:0.03
    6:0.09
    7:0.09
    8:0.16
    9:0.08
    10:0.14
    11:0.06
    Negative Logits
    thood
    -1.03
    ̶
    -1.01
    aign
    -0.94
    ortality
    -0.94
    raints
    -0.91
    aton
    -0.90
    upon
    -0.90
    alla
    -0.89
    ainment
    -0.88
    rentice
    -0.88
    POSITIVE LOGITS
     occasion
    1.11
     behalf
    1.08
    etheless
    1.02
     Logged
    1.00
     occasions
    0.95
    btn
    0.94
     occas
    0.93
     HDR
    0.89
     carpet
    0.89
     bluff
    0.89
    Activations Density 0.378%

    No Known Activations