© 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. 39490
    Prev
    Next
    INDEX
    Explanations

    locations or venues where events take place

    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
    2:0.20
    3:0.10
    4:0.15
    5:0.03
    6:0.06
    7:0.04
    8:0.10
    9:0.04
    10:0.10
    11:0.09
    Negative Logits
     oneself
    -1.79
    idious
    -1.77
     positives
    -1.74
     alien
    -1.64
     underestimated
    -1.62
     uniquely
    -1.61
    alien
    -1.52
    annot
    -1.52
     expend
    -1.52
    achev
    -1.51
    POSITIVE LOGITS
     Pavilion
    2.01
     Amph
    1.94
     Resort
    1.92
     Ranch
    1.87
     Civic
    1.78
    iseum
    1.75
     Wildlife
    1.71
     Memorial
    1.68
     Expo
    1.68
     offices
    1.68
    Activations Density 0.241%

    No Known Activations