© 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. 10-ATT-KK
    11. 11902
    Prev
    Next
    INDEX
    Explanations

    negative sentiment or criticism

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-att-kk
    Configuration
    ckkissane/attn-saes-gpt2-small-all-layers/gpt2-small_L10_Hcat_z_lr1.20e-03_l11.30e+00_ds24576_bs4096_dc1.00e-05_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.10.attn.hook_z
    Hook Layer
    10
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Head Attr Weights
    0:0.10
    1:0.07
    2:0.09
    3:0.07
    4:0.08
    5:0.06
    6:0.09
    7:0.08
    8:0.07
    9:0.06
    10:0.10
    11:0.07
    Negative Logits
     Rings
    -2.76
     Olympus
    -2.75
     Petersen
    -2.67
     Continental
    -2.57
    bet
    -2.47
     Siem
    -2.46
     Fore
    -2.34
     Horse
    -2.34
     USPS
    -2.34
     bets
    -2.33
    POSITIVE LOGITS
     filibuster
    2.90
     caf
    2.77
    adr
    2.49
    orial
    2.46
    rendered
    2.45
     coloring
    2.44
    Ore
    2.37
     randomized
    2.37
     cafeteria
    2.35
     Caf
    2.34
    Activations Density 0.000%

    No Known Activations