© 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. 5-ATT-KK
    11. 39828
    Prev
    Next
    INDEX
    Explanations

    actions and decisions made by legislative bodies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L5_Hcat_z_lr1.20e-03_l11.00e+00_ds49152_bs4096_dc1.00e-06_rsanthropic_rie25000_nr4_v9.pt
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    49,152
    Data Type
    float32
    Hook Name
    blocks.5.attn.hook_z
    Hook Layer
    5
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Head Attr Weights
    0:0.02
    1:0.01
    2:0.06
    3:0.06
    4:0.04
    5:0.06
    6:0.04
    7:0.06
    8:0.04
    9:0.06
    10:0.36
    11:0.15
    Negative Logits
     subsidiary
    -1.53
     cryst
    -1.48
     Krypt
    -1.43
     parent
    -1.42
     lesbian
    -1.31
     crystals
    -1.29
     label
    -1.28
     adoptive
    -1.24
    "}],"
    -1.23
     token
    -1.22
    POSITIVE LOGITS
    raft
    1.70
    hou
    1.63
    govtrack
    1.53
    NetMessage
    1.50
    odder
    1.48
    seless
    1.46
    endas
    1.45
    vernment
    1.43
    incinn
    1.43
    erity
    1.42
    Activations Density 0.019%

    No Known Activations