© 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. 39500
    Prev
    Next
    INDEX
    Explanations

    topics related to debates and discussions, particularly those that are heated or contentious

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Head Attr Weights
    0:0.02
    1:0.02
    2:0.05
    3:0.06
    4:0.05
    5:0.05
    6:0.03
    7:0.07
    8:0.03
    9:0.05
    10:0.38
    11:0.13
    Negative Logits
     inherited
    -1.58
     loans
    -1.50
     protector
    -1.50
     Reaper
    -1.49
     burg
    -1.46
     mortgages
    -1.45
     accessory
    -1.45
     estates
    -1.45
     loan
    -1.44
     predecessor
    -1.43
    POSITIVE LOGITS
    Discussion
    2.17
     discussion
    1.98
     Debate
    1.85
     debating
    1.85
     debate
    1.77
     Discussion
    1.73
     debated
    1.70
    NetMessage
    1.67
    RAFT
    1.61
    swers
    1.60
    Activations Density 0.184%

    No Known Activations