© 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. 6657
    Prev
    Next
    INDEX
    Explanations

    references to astronomical phenomena and their characteristics

    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
    0:0.32
    1:0.05
    2:0.05
    3:0.10
    4:0.08
    5:0.02
    6:0.05
    7:0.06
    8:0.02
    9:0.07
    10:0.05
    11:0.08
    Negative Logits
    ilitation
    -4.18
    ufact
    -3.89
     Slaughter
    -3.65
     Duff
    -3.60
    ewater
    -3.53
     Rape
    -3.52
    aukee
    -3.52
     Bangl
    -3.49
     Bangladesh
    -3.40
    igslist
    -3.29
    POSITIVE LOGITS
     astronomers
    8.66
     astronomer
    8.07
     galaxies
    7.53
     astronomy
    7.50
     Astron
    7.47
     telescopes
    7.43
     astroph
    7.42
     telescope
    7.19
     Hubble
    7.14
     galaxy
    7.12
    Activations Density 0.531%

    No Known Activations