© 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. 38208
    Prev
    Next
    INDEX
    Explanations

    sentiments related to the threat of climate change among different political groups

    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
    0:0.05
    1:0.03
    2:0.10
    3:0.29
    4:0.06
    5:0.05
    6:0.02
    7:0.04
    8:0.05
    9:0.09
    10:0.10
    11:0.07
    Negative Logits
     countless
    -1.60
     innumerable
    -1.59
    NetMessage
    -1.50
    AUT
    -1.50
     legions
    -1.50
     comrades
    -1.49
     understandably
    -1.48
     irresist
    -1.41
    fortunately
    -1.37
     ANGEL
    -1.37
    POSITIVE LOGITS
    chu
    1.65
     unspecified
    1.62
    /"
    1.52
     or
    1.49
    onga
    1.47
     REUTERS
    1.43
    isine
    1.43
    ificial
    1.43
     guiName
    1.42
    hig
    1.41
    Activations Density 0.180%

    No Known Activations